© 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. 43424
    Prev
    Next
    INDEX
    Explanations

    obese individuals, difficulty, balance

    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
    constru
    0.46
    el
    0.46
    al
    0.46
    insurance
    0.45
    can
    0.45
     usted
    0.44
    know
    0.44
    ’
    0.43
    quit
    0.43
    click
    0.42
    POSITIVE LOGITS
     CommandLine
    0.50
     repositories
    0.48
     boating
    0.47
    が出て
    0.47
    나
    0.47
     bitOp
    0.47
    ধানা
    0.46
     posicao
    0.46
     regenv
    0.46
    ৰি
    0.45
    Activations Density 0.001%

    No Known Activations