© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13452
    Prev
    Next
    INDEX
    Explanations

    names followed by actions

    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_7_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
    ’
    2.62
    '
    2.53
     instinctively
    1.86
    ʼ
    1.84
    さんは
    1.73
     brag
    1.66
    ův
    1.62
    '...
    1.61
     was
    1.60
     swore
    1.59
    POSITIVE LOGITS
    tied
    1.78
     geographic
    1.67
     geographical
    1.65
    <0x0D>
    1.62
     geospatial
    1.58
     lexical
    1.57
    บริเวณ
    1.56
     Mutable
    1.55
    drawn
    1.53
     PSI
    1.53
    Activations Density 0.042%

    No Known Activations