© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 3072
    Prev
    Next
    INDEX
    Explanations

    possessive women's or "when" questions

    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
     even
    -0.82
     on
    -0.72
     with
    -0.71
    集成
    -0.69
     原
    -0.69
    ‘
    -0.68
     and
    -0.68
     AI
    -0.66
     became
    -0.65
    ゲル
    -0.64
    POSITIVE LOGITS
    ciler
    1.02
    possibly
    1.00
     vernie
    0.95
    perhaps
    0.95
    probably
    0.91
     stehenden
    0.89
    sees
    0.89
    妧
    0.89
    enie
    0.89
    *;
    0.88
    Activations Density 0.000%

    No Known Activations