© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64811
    Prev
    Next
    INDEX
    Explanations

    code verbs and nouns

    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_22/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
     that
    -0.98
    جموع
    -0.95
     our
    -0.94
     everything
    -0.91
     aquesta
    -0.90
     each
    -0.90
    $(\
    -0.88
     anything
    -0.87
     some
    -0.86
     vó
    -0.86
    POSITIVE LOGITS
    Heer
    0.91
     dissatisfaction
    0.91
    äld
    0.90
    ร้าน
    0.89
    Μ
    0.88
    Siapa
    0.87
    ę
    0.84
     nabíd
    0.83
    เมื่อ
    0.83
     discontent
    0.82
    Activations Density 0.001%

    No Known Activations