© 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. 11768
    Prev
    Next
    INDEX
    Explanations

    requests for detailed, procedural information or guidance.

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

    things

    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
     be
    0.92
     e
    0.59
     d
    0.57
     и
    0.57
    ad
    0.54
    wa
    0.54
     degli
    0.54
     و
    0.54
    و
    0.53
     and
    0.52
    POSITIVE LOGITS
    h
    0.89
    东西
    0.71
    t
    0.68
    g
    0.68
     Люди
    0.67
    gF
    0.66
     needful
    0.64
     ludzie
    0.63
     люди
    0.62
    С
    0.61
    Activations Density 0.086%

    No Known Activations