© 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. 36310
    Prev
    Next
    INDEX
    Explanations

    legal terms and origins

    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
    jammer
    0.46
    ،
    0.46
     ڕ
    0.45
    damian
    0.45
    argaan
    0.44
    pher
    0.42
     العامة
    0.42
    isht
    0.41
    arnos
    0.41
    anyol
    0.41
    POSITIVE LOGITS
     humans
    0.46
    सेट
    0.44
    தின
    0.44
    咘
    0.44
     greed
    0.43
     איך
    0.43
    <unused82>
    0.43
     numerador
    0.43
    ப்ட
    0.43
    जन्
    0.42
    Activations Density 0.001%

    No Known Activations