© 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
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1739
    Prev
    Next
    INDEX
    Explanations

    years and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ９
    1.31
    近代
    1.29
    ८
    1.28
    十九
    1.27
    ९
    1.26
    ৮
    1.25
    ８
    1.23
    ೮
    1.20
    ๘
    1.20
     décadas
    1.20
    POSITIVE LOGITS
     nor
    0.75
     or
    0.74
    experienced
    0.72
     или
    0.72
    ingle
    0.71
     significant
    0.69
     contested
    0.68
     marginal
    0.68
     obvious
    0.66
     candidates
    0.65
    Activations Density 0.266%

    No Known Activations