© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1500
    Prev
    Next
    INDEX
    Explanations

    showing visuals or depictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     Committees
    1.48
     conhece
    1.46
    гово
    1.45
     kurul
    1.44
     lifelong
    1.44
     ido
    1.43
    inerary
    1.43
    璺
    1.42
    闶
    1.42
    岭
    1.41
    POSITIVE LOGITS
     depicting
    1.71
     illustrating
    1.62
    screenshot
    1.50
     mockup
    1.47
     showing
    1.37
     depiction
    1.37
     mostrando
    1.35
     representación
    1.34
    Screenshot
    1.34
    showing
    1.33
    Activations Density 1.298%

    No Known Activations