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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71359
    Prev
    Next
    INDEX
    Explanations

    multiple suggestions

    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
    u
    0.50
     til
    0.47
     with
    0.42
    c
    0.40
    gunakan
    0.40
     who
    0.39
    ella
    0.39
    a
    0.39
     attempt
    0.38
     be
    0.38
    POSITIVE LOGITS
     ইতো
    0.50
    逛
    0.50
     приорите
    0.48
     múltiples
    0.47
     QuickBooks
    0.47
     saludables
    0.46
     fintech
    0.46
     цих
    0.46
     этих
    0.45
     overarching
    0.45
    Activations Density 0.001%

    No Known Activations