© 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. 82941
    Prev
    Next
    INDEX
    Explanations

    file paths and URLs

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

    The neuron fires on quotation and apostrophe punctuation (single or double quotes).

    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
     theatres
    -0.98
    異
    -0.88
     Anges
    -0.80
     proof
    -0.79
    随后
    -0.77
    かない
    -0.77
     datatype
    -0.77
     thong
    -0.76
    acety
    -0.74
     mines
    -0.73
    POSITIVE LOGITS
    Bugs
    0.75
     ihan
    0.73
     dwell
    0.73
     saman
    0.73
    ுகள்
    0.71
    忿
    0.70
     Dieses
    0.69
     mirip
    0.69
    卽
    0.69
     labdar
    0.68
    Activations Density 0.232%

    No Known Activations