© 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. 5989
    Prev
    Next
    INDEX
    Explanations

    Condition Technique

    np_acts-logits-general · gemini-2.5-flash-lite

    specialized, domain-specific terminology—especially names of components, subsystems, and formal constructs across technical subjects.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    तोंडा
    0.35
     immoral
    0.35
    螅
    0.34
    鸴
    0.32
     samme
    0.32
    GTBase
    0.32
     identifik
    0.31
     మంచి
    0.31
     ഭക്ഷ
    0.31
    राधिक
    0.31
    POSITIVE LOGITS
    /
    0.53
    -
    0.47
    6
    0.46
     and
    0.45
    8
    0.43
    4
    0.41
    .
    0.40
    +
    0.40
    5
    0.40
    ,
    0.39
    Activations Density 0.703%

    No Known Activations