© 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. 241246
    Prev
    Next
    INDEX
    Explanations

    Old Testament

    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
     besuchen
    0.52
    ະລ
    0.49
     fördern
    0.48
     từng
    0.48
    䀓
    0.48
     الخامسه
    0.48
     vivir
    0.47
     moverse
    0.47
     sobrevivir
    0.47
    nicima
    0.46
    POSITIVE LOGITS
    IS
    0.61
    ES
    0.56
    TEST
    0.51
    NS
    0.49
    NOT
    0.48
     k
    0.48
    );
    0.48
     ES
    0.47
     bind
    0.46
    ком
    0.45
    Activations Density 0.000%

    No Known Activations