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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 108291
    Prev
    Next
    INDEX
    Explanations

    code punctuation and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     nämlich
    -0.81
     シャ
    -0.79
     Inſ
    -0.78
     Tuttavia
    -0.77
    őt
    -0.77
    always
    -0.76
     متعل
    -0.75
    Однако
    -0.73
     Pert
    -0.73
    Toy
    -0.73
    POSITIVE LOGITS
    ?
    2.06
    ?”
    1.40
    ?"
    1.27
     try
    1.17
    ?)
    1.14
    ?).
    1.06
    ?</
    1.02
    try
    0.96
    ?;
    0.93
     required
    0.92
    Activations Density 0.003%

    No Known Activations