© 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. 10-GEMMASCOPE-RES-131K
    4. 128419
    Prev
    Next
    INDEX
    Explanations

    nation

    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
    idjan
    -3.06
     économique
    -2.25
    wahati
    -2.19
     乗り
    -2.17
    inctions
    -2.14
    咐
    -2.09
    民众
    -2.08
     ouverture
    -2.06
    going
    -2.06
    AL
    -2.06
    POSITIVE LOGITS
    {
    2.55
     voor
    2.39
    i
    2.38
    ྜ
    2.19
    </sup>
    2.19
    </b>
    2.17
    %
    2.17
    ↵
    2.16
     \
    2.11
    );
    2.06
    Activations Density 0.008%

    No Known Activations