© 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-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 32101
    Prev
    Next
    INDEX
    Explanations

    punitive damages

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

    Trust Chain, hunting

    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
    ITEM
    0.48
    टर
    0.47
    Punjab
    0.46
    ब्ल्यू
    0.46
    डेजा
    0.45
     отвер
    0.45
    NSW
    0.45
    Č
    0.45
    TRY
    0.44
    ength
    0.43
    POSITIVE LOGITS
     munt
    0.48
     crepe
    0.47
     trái
    0.45
     galactic
    0.45
     passage
    0.44
     bass
    0.44
     hunting
    0.44
     গিয়ে
    0.44
     crest
    0.44
     cre
    0.43
    Activations Density 0.000%

    No Known Activations