© 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. 116511
    Prev
    Next
    INDEX
    Explanations

    code blocks and lists

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

    The neuron fires on long runs of consecutive space characters (i.e. indentation in the text).

    oai_token-act-pair · o4-miniTriggered 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
    ňuje
    -0.93
     ciągu
    -0.81
     still
    -0.77
     CRM
    -0.75
     just
    -0.75
     FIG
    -0.74
    掛
    -0.74
    隈
    -0.73
    安倍
    -0.71
    ()]
    
    -0.70
    POSITIVE LOGITS
    item
    0.96
    IENCE
    0.86
     li
    0.84
     case
    0.82
    case
    0.81
     naturligt
    0.81
    kedés
    0.81
     overpowering
    0.79
     Talley
    0.79
     podéis
    0.79
    Activations Density 0.002%

    No Known Activations