© 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-65K
    7. 7765
    Prev
    Next
    INDEX
    Explanations

    requests for specific information or software recommendations.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    show me

    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_65k_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
    on
    0.73
    -
    0.70
    '
    0.63
    ν
    0.59
    er
    0.58
    inating
    0.58
    wave
    0.57
    ish
    0.56
    aile
    0.56
    times
    0.55
    POSITIVE LOGITS
     Escherichia
    0.58
    ſelf
    0.57
     assurances
    0.53
     in
    0.53
     syarat
    0.52
     ૩
    0.52
     persönlich
    0.52
     about
    0.51
    $,
    0.50
     この
    0.50
    Activations Density 0.164%

    No Known Activations