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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110539
    Prev
    Next
    INDEX
    Explanations

    courtroom terms and judges

    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
    acters
    -0.99
    mle
    -0.77
     UserProfile
    -0.76
    メソッド
    -0.76
    ributors
    -0.75
    يط
    -0.74
    हम
    -0.74
     vacation
    -0.74
    mudi
    -0.73
    gulier
    -0.73
    POSITIVE LOGITS
     litig
    0.72
    Kontra
    0.71
    reject
    0.71
    ߟ
    0.69
    tikus
    0.69
    丘
    0.69
     lentil
    0.69
     INVOLVED
    0.69
     Strokes
    0.69
    Apex
    0.68
    Activations Density 0.037%

    No Known Activations