© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 40613
    Prev
    Next
    INDEX
    Explanations

    Zelda, shear, CNN, pulp fiction

    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
    。
    0.53
     mercantile
    0.49
     democracies
    0.43
     extremists
    0.43
     coalitions
    0.43
     reigning
    0.43
     actifs
    0.42
     bureaucrats
    0.42
     dependents
    0.42
     জোট
    0.41
    POSITIVE LOGITS
    at
    0.48
    ิ
    0.48
     was
    0.46
    诒
    0.46
    was
    0.46
    it
    0.46
    data
    0.46
     состави
    0.46
    errors
    0.45
     Typography
    0.45
    Activations Density 0.013%

    No Known Activations