© 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. 10-GEMMASCOPE-RES-131K
    4. 42888
    Prev
    Next
    INDEX
    Explanations

    ruling party, class, regime, or decision

    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_10/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
    𐍆
    -2.98
     '
    -2.69
    癶
    -2.13
    ’
    -2.09
    蹋
    -2.09
    s
    -1.99
     Scritto
    -1.95
     المعيار
    -1.95
    ❇
    -1.92
     Danmark
    -1.88
    POSITIVE LOGITS
     renowned
    2.78
    );
    2.45
     somewhat
    2.44
    But
    2.42
     predominantly
    2.33
    i
    2.31
     ),
    2.30
     able
    2.30
    ;.
    2.28
     famed
    2.23
    Activations Density 0.004%

    No Known Activations