© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3297
    Prev
    Next
    INDEX
    Explanations

    trying to solve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     esfuerzo
    1.09
     tentar
    1.06
     کوشش
    1.05
    طلب
    1.04
     ശ്രമ
    1.04
    惆
    1.03
     esfuerzos
    1.03
    成为
    1.02
    成為
    0.98
     ಎಷ್ಟು
    0.97
    POSITIVE LOGITS
    s
    0.62
    ensive
    0.59
     formative
    0.57
    <0xC2>
    0.57
     reg
    0.56
    Info
    0.55
    \|
    0.54
    de
    0.54
    dist
    0.54
    рующие
    0.54
    Activations Density 0.049%

    No Known Activations