© 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. 231839
    Prev
    Next
    INDEX
    Explanations

    security, attack, pig, bread

    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
     Municipio
    0.54
     Duy
    0.48
     Celle
    0.47
    ’
    0.47
    am
    0.45
     Diamond
    0.44
     Tu
    0.44
     Lake
    0.43
     دى
    0.43
    梫
    0.43
    POSITIVE LOGITS
    จัย
    0.57
    fromj
    0.52
    ちに
    0.52
    の話
    0.51
    臓
    0.50
     fanfare
    0.50
    ्यता
    0.49
    紳
    0.49
    posting
    0.49
     blotting
    0.48
    Activations Density 0.001%

    No Known Activations