© 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. 41840
    Prev
    Next
    INDEX
    Explanations

    variations depend on context

    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
    purse
    0.44
    ٢
    0.43
    insulated
    0.43
    BA
    0.42
    South
    0.42
    sl
    0.42
    のない
    0.42
    \,\
    0.42
    computing
    0.42
    ċ
    0.40
    POSITIVE LOGITS
     기본
    0.48
     tumorigen
    0.47
     profiles
    0.46
     catégories
    0.46
     participates
    0.45
     DUE
    0.45
     фаразы
    0.45
     specifies
    0.45
     síntomas
    0.45
     pathogenesis
    0.44
    Activations Density 0.010%

    No Known Activations