© 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. 13643
    Prev
    Next
    INDEX
    Explanations

    n-way k-shot n-grams k-fold p-adic k-hop harmonic

    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_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
    ії
    0.46
     wry
    0.45
     ትንሽ
    0.44
     ქ
    0.44
    خلي
    0.44
    一个小
    0.43
    wyd
    0.43
     CtApp
    0.42
     една
    0.42
     ног
    0.41
    POSITIVE LOGITS
    -
    0.61
     environments
    0.47
     types
    0.47
     filters
    0.46
     individual
    0.45
     ranging
    0.45
     avenues
    0.44
     machines
    0.44
     sensors
    0.44
     versions
    0.44
    Activations Density 0.001%

    No Known Activations