© 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. 98268
    Prev
    Next
    INDEX
    Explanations

    code conditional statements

    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
    십시오
    -0.91
    òm
    -0.89
    ;
    -0.86
    findOneAndUpdate
    -0.78
    ッド
    -0.77
     even
    -0.76
    mae
    -0.75
    :
    -0.75
     även
    -0.75
    Particular
    -0.75
    POSITIVE LOGITS
    BeginContext
    0.90
     /*
    0.90
    Σε
    0.84
    UTUP
    0.83
    eqn
    0.82
    ֗
    0.81
     Requirement
    0.81
    strftime
    0.80
     Athletes
    0.80
     ボックス
    0.79
    Activations Density 0.008%

    No Known Activations