© 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. 6067
    Prev
    Next
    INDEX
    Explanations

    requests for explicit or inappropriate content.

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

    unwanted urges or biases

    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
    ي
    0.70
    i
    0.61
     aŭ
    0.60
     ankaŭ
    0.60
    ካከል
    0.60
    /
    0.59
     או
    0.58
    ه
    0.57
     även
    0.56
    kowe
    0.55
    POSITIVE LOGITS
    ients
    0.61
    ap
    0.55
     a
    0.54
    ignal
    0.50
    ടൊപ്പം
    0.50
     यूँ
    0.50
    ville
    0.49
    踏
    0.49
    land
    0.47
    ակի
    0.47
    Activations Density 0.240%

    No Known Activations