© 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. 3129
    Prev
    Next
    INDEX
    Explanations

    breaking down topics

    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
    <unused1411>
    1.14
     情報
    1.08
     వడయార్
    1.07
    <unused1308>
    1.06
    <unused1479>
    1.05
     noirâtres
    1.05
    <unused807>
    1.05
    <unused1498>
    1.05
    <unused25>
    1.04
    <unused1266>
    1.04
    POSITIVE LOGITS
    /
    0.82
    -
    0.78
    ?
    0.70
    '
    0.63
    ?!
    0.63
    be
    0.61
     /
    0.61
    ？！
    0.61
    +
    0.61
    @
    0.60
    Activations Density 1.219%

    No Known Activations