© 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. 40-GEMMASCOPE-2-RES-262K
    7. 3864
    Prev
    Next
    INDEX
    Explanations

    field length and type definitions

    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_40_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
    宽
    0.44
    īt
    0.39
    Enlaces
    0.37
    橫
    0.37
    holder
    0.37
    ViewState
    0.35
    orgen
    0.35
    ([[
    0.35
     mView
    0.35
     DATE
    0.34
    POSITIVE LOGITS
     러시아
    0.46
    addAnimation
    0.40
    ロシア
    0.40
     Russland
    0.39
     России
    0.38
    まずは
    0.38
     nikdy
    0.38
     reactors
    0.38
    auté
    0.38
     ببین
    0.38
    Activations Density 0.003%

    No Known Activations