© 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. 206155
    Prev
    Next
    INDEX
    Explanations

    owned or manage

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

    key, involved, cards, need, one

    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
     случаи
    0.47
    刺
    0.46
    మారు
    0.46
    为何
    0.45
    汽车
    0.44
    िल
    0.43
     sớm
    0.43
    మి
    0.43
    ়
    0.43
     möglichen
    0.42
    POSITIVE LOGITS
    elernt
    0.49
    <0x0D>
    0.49
     Abyss
    0.48
     pr
    0.46
     अतीत
    0.46
    Anal
    0.46
     বিশ্লে
    0.46
     logger
    0.45
    anterie
    0.45
     temperament
    0.45
    Activations Density 0.001%

    No Known Activations