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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13852
    Prev
    Next
    INDEX
    Explanations

    physical reactions and sensations

    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
    ukses
    -1.08
     свой
    -1.06
     Dopo
    -1.02
     能
    -1.01
    May
    -0.99
     ベクトル
    -0.98
    ibição
    -0.97
    Unless
    -0.96
    will
    -0.96
    ();
    -0.96
    POSITIVE LOGITS
    筚
    1.03
     juſt
    0.99
    ạch
    0.99
    inerja
    0.99
     blanche
    0.98
    bonsoir
    0.98
    aneity
    0.97
    </tfoot>
    0.96
     faca
    0.96
     zaradi
    0.96
    Activations Density 0.014%

    No Known Activations