© 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. 17-GEMMASCOPE-2-RES-16K
    7. 14720
    Prev
    Next
    INDEX
    Explanations

    comments, coding, research, statements

    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_17_width_16k_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
    ☄
    1.20
    ína
    1.15
    類的
    1.09
    फाइनल
    1.08
    showroom
    1.08
     humanidad
    1.08
    ównie
    1.06
     sitt
    1.06
     fierce
    1.04
     LoginPage
    1.04
    POSITIVE LOGITS
    трен
    1.12
    و
    1.06
    statements
    1.03
     menores
    1.01
    ደን
    0.95
     Statement
    0.95
    Statement
    0.93
     ограни
    0.92
    ح
    0.90
    anées
    0.90
    Activations Density 0.001%

    No Known Activations