© 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. 1483
    Prev
    Next
    INDEX
    Explanations

    word formation Russian Spanish

    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
     travailler
    0.96
     condesc
    0.91
     slander
    0.91
     Meinung
    0.90
     Zasshi
    0.88
    副作用
    0.87
     bewegen
    0.87
     店
    0.87
     llevará
    0.86
    妏
    0.86
    POSITIVE LOGITS
     of
    1.45
    ‌های
    1.20
     של
    1.17
     của
    1.16
     της
    1.14
    های
    1.14
     های
    1.13
     التي
    1.08
    of
    1.07
    \'{
    1.01
    Activations Density 0.079%

    No Known Activations