© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47603
    Prev
    Next
    INDEX
    Explanations

    discuss conversions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ess
    0.53
    in
    0.50
    SU
    0.50
    an
    0.49
    '
    0.49
     Max
    0.48
    ed
    0.47
    u
    0.46
    th
    0.46
     Centers
    0.45
    POSITIVE LOGITS
     लाहिड़ी
    0.54
     ਦਵਾਈ
    0.54
     finalidad
    0.54
     밝혔다
    0.53
     אך
    0.52
     predominance
    0.52
     prerog
    0.52
     전환
    0.52
     resumption
    0.51
     paiement
    0.51
    Activations Density 0.003%

    No Known Activations