© 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-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 15146
    Prev
    Next
    INDEX
    Explanations

    output=

    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
    님
    1.00
     putea
    0.99
     minify
    0.98
    سن
    0.97
     blemishes
    0.97
    遜
    0.96
    国道
    0.95
    INGTON
    0.93
     eased
    0.93
     limousine
    0.92
    POSITIVE LOGITS
    spe
    1.12
    pe
    0.99
    ulares
    0.99
    最後まで
    0.98
    sil
    0.98
    وامل
    0.97
     ín
    0.97
    юй
    0.95
     ষ
    0.95
     exibir
    0.93
    Activations Density 0.001%

    No Known Activations