© 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. 111490
    Prev
    Next
    INDEX
    Explanations

    programming language syntax

    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
     p
    0.58
     x
    0.55
    .
    0.54
    _
    0.54
     location
    0.53
     type
    0.52
    id
    0.52
    :
    0.52
    str
    0.52
    x
    0.52
    POSITIVE LOGITS
     специальные
    0.54
    Subgraph
    0.52
     Elektrokhimiya
    0.52
    撵
    0.51
    ંત્રણ
    0.50
    ActivityResult
    0.49
    
    0.49
    ద్ధి
    0.48
    SpriteCollision
    0.48
    ListItemIcon
    0.47
    Activations Density 0.024%

    No Known Activations