© 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. 202838
    Prev
    Next
    INDEX
    Explanations

    was forbidden, finds., Initiatives and, Guinness., Complete the, minute due, on Common, latex bed, white Barbie

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

    specific items, dates, or actions

    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
     острова
    0.46
    략
    0.45
     обязан
    0.44
    ске
    0.42
     모습을
    0.42
     कैटरीना
    0.41
    ᴙ
    0.40
     व्यापक
    0.39
     Captain
    0.38
    RANK
    0.38
    POSITIVE LOGITS
     be
    0.57
     mem
    0.51
     kênh
    0.49
     sanit
    0.49
    qd
    0.48
     prayed
    0.47
     kq
    0.46
     rése
    0.45
    コ
    0.45
     sei
    0.45
    Activations Density 0.000%

    No Known Activations