© 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. 2550
    Prev
    Next
    INDEX
    Explanations

    quotes and internal states

    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
    गौरतलब
    0.75
    ریت
    0.64
    asjonen
    0.63
    issante
    0.62
    ങ്
    0.62
    ();//
    0.61
    %@",
    0.61
     गौरतलब
    0.60
    വിത
    0.59
    ()");
    0.59
    POSITIVE LOGITS
     granular
    0.70
     ("
    0.66
     "...
    0.64
     "[
    0.64
     "
    0.63
     ofertas
    0.59
     albo
    0.55
     ("[
    0.54
     ví
    0.54
     marvel
    0.54
    Activations Density 0.367%

    No Known Activations