© 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. 157203
    Prev
    Next
    INDEX
    Explanations

    trademarks, authors, antimicrobial, gas, press

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

    resume, immunity, flushing

    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
     estudia
    0.51
     زی
    0.48
     klasik
    0.46
     Akadem
    0.45
     estudiar
    0.45
     Studien
    0.45
     சேன
    0.44
    .&
    0.44
     clings
    0.44
    ત્મક
    0.44
    POSITIVE LOGITS
    equation
    0.66
    function
    0.53
    freq
    0.50
    incent
    0.49
    LOCK
    0.49
    LOG
    0.48
    warning
    0.48
    好奇
    0.47
    breaking
    0.47
    悬
    0.47
    Activations Density 0.000%

    No Known Activations