© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75728
    Prev
    Next
    INDEX
    Explanations

    metadata attributes and values

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on numeric tokens (i.e. sequences of digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    HTML/XML metadata tags and attributes, particularly those related to document properties like "title", "meta", "name", "keywords", and "charset".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    document metadata and header fields across structured formats (HTML tags, YAML front matter, JSON keys, and similar).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idleness
    -0.70
     Quaker
    -0.66
    بن
    -0.63
    雎
    -0.63
    udh
    -0.61
    來到
    -0.60
    あら
    -0.60
     daughters
    -0.60
     menegaskan
    -0.60
    Qu
    -0.59
    POSITIVE LOGITS
    ajes
    0.79
     babak
    0.75
     diluted
    0.72
    েই
    0.69
     यह
    0.69
     πυ
    0.69
    Corrected
    0.66
    Retain
    0.66
    Critique
    0.65
     Warren
    0.64
    Activations Density 0.074%

    No Known Activations