© 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. 2581
    Prev
    Next
    INDEX
    Explanations

    the short answer is

    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
     stuffed
    1.11
    in
    1.01
    Suggested
    0.99
    flap
    0.94
     под
    0.94
     cele
    0.93
    e
    0.93
    Grpc
    0.92
    দু
    0.92
    ת
    0.91
    POSITIVE LOGITS
     importantly
    1.04
    ことになる
    1.04
     Vậy
    0.95
    !--
    0.93
    这也是
    0.91
    sächlich
    0.90
    }\|_{
    0.89
    мум
    0.89
    kül
    0.88
     Springsteen
    0.86
    Activations Density 0.107%

    No Known Activations