© 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. 120287
    Prev
    Next
    INDEX
    Explanations

    "cannot" be redeemed or transferred

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

    descriptions or missing information

    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
    影響
    0.44
     essentially
    0.43
    r
    0.43
    of
    0.41
    Sl
    0.41
    NumberOf
    0.40
    0
    0.40
    sl
    0.40
    ките
    0.39
     می‌
    0.39
    POSITIVE LOGITS
    ভিল
    0.52
    ეცი
    0.46
     Questa
    0.46
    带来
    0.45
    न्देल
    0.44
     আওয়ামীলীগ
    0.44
     Apesar
    0.44
     বাড়ী
    0.44
    🍭
    0.44
    ╡
    0.44
    Activations Density 0.001%

    No Known Activations