© 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. 758
    Prev
    Next
    INDEX
    Explanations

    requests for harmful, explicit, or unethical content involving violence and abuse.

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

    argument, effect, issue, term, request

    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
    :
    0.31
    。
    0.27
    ।
    0.26
    .
    0.26
    \
    0.25
    ：
    0.25
    The
    0.24
    '.
    0.24
    /
    0.24
    )
    0.24
    POSITIVE LOGITS
     connues
    0.21
     vuelto
    0.21
     beho
    0.21
     souvent
    0.20
    ныгы
    0.20
    тился
    0.20
     envolve
    0.19
     culminates
    0.19
     évidemment
    0.19
     ismer
    0.19
    Activations Density 0.530%

    No Known Activations