© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 1957
    Prev
    Next
    INDEX
    Explanations

    describing verbs and nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    0.29
     OL
    0.27
    OR
    0.26
     EX
    0.26
     FL
    0.25
    ↵
    0.24
     IL
    0.24
    ਥ
    0.24
    EX
    0.23
     OR
    0.23
    POSITIVE LOGITS
    🤛
    0.42
    ológica
    0.41
    amentales
    0.41
    ativos
    0.41
    🚥
    0.40
    🍢
    0.40
    ainment
    0.40
    yect
    0.40
    🔩
    0.39
    🐃
    0.39
    Activations Density 0.210%

    No Known Activations