© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 763
    Prev
    Next
    INDEX
    Explanations

    introducing summary or conclusion

    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
     Forms
    0.84
    ㄷ
    0.75
    cursion
    0.73
     vic
    0.73
     (~
    0.70
     Form
    0.70
     FORM
    0.70
     (>
    0.67
     forment
    0.67
    >();
    0.66
    POSITIVE LOGITS
     meantime
    1.40
    此同时
    1.35
    此外
    1.34
    swering
    1.34
     conversely
    1.34
    fact
    1.32
    тім
    1.31
     fact
    1.30
     truth
    1.26
     কথায়
    1.25
    Activations Density 1.037%

    No Known Activations