© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100765
    Prev
    Next
    INDEX
    Explanations

    political figures and officials

    np_acts-logits-general · gemini-2.5-flash-lite

    physical awareness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ｆ
    0.53
    urètre
    0.50
     contrôle
    0.50
    ăți
    0.47
    ogène
    0.47
    Ꮈ
    0.47
    ಮಗೆ
    0.46
     контроли
    0.46
    Ꮁ
    0.46
     rappelle
    0.45
    POSITIVE LOGITS
    ,
    0.54
     держа
    0.46
     Bar
    0.45
     by
    0.44
     Line
    0.43
    IL
    0.43
    ús
    0.42
    ulare
    0.42
     zugleich
    0.42
     Spieler
    0.41
    Activations Density 0.001%

    No Known Activations