© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144469
    Prev
    Next
    INDEX
    Explanations

    Newton's method or yes/no answers

    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
     incentiv
    0.52
     indemn
    0.46
    <unused512>
    0.46
     dehuman
    0.46
     kone
    0.45
    <unused480>
    0.44
     také
    0.43
     hinzufügen
    0.43
    <unused639>
    0.42
     incentives
    0.42
    POSITIVE LOGITS
    üm
    0.57
     офис
    0.52
    Department
    0.48
     от
    0.48
    ъ
    0.48
    Cheng
    0.47
    FORM
    0.46
     Се
    0.45
    !,
    0.44
    Family
    0.43
    Activations Density 0.011%

    No Known Activations