© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59285
    Prev
    Next
    INDEX
    Explanations

    list starters and code prefixes

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

    The neuron is triggered by large runs of leading whitespace (indentation) in code lines.

    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
    geschichte
    -0.83
    var
    -0.82
    вар
    -0.81
    BufferedReader
    -0.78
    cshtml
    -0.78
    )<\
    -0.76
    }};
    -0.75
    ']?>
    -0.74
    ):=\
    -0.74
    писать
    -0.73
    POSITIVE LOGITS
    Ḳ
    0.93
     FALSE
    0.87
     Roswell
    0.86
     Duluth
    0.82
     Rango
    0.78
     Chaldean
    0.76
     Punj
    0.76
     Gummi
    0.75
     Glacial
    0.75
    ennia
    0.75
    Activations Density 0.017%

    No Known Activations