© 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. 13-GEMMASCOPE-2-RES-65K
    7. 1886
    Prev
    Next
    INDEX
    Explanations

    free tier, duty to

    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_13_width_65k_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
     Bender
    1.33
     Harr
    1.31
     Bud
    1.28
    幡
    1.19
    ंसक
    1.18
     Represent
    1.17
     bud
    1.16
    Hann
    1.14
     Busch
    1.14
    )++;
    1.13
    POSITIVE LOGITS
    bies
    1.85
    🆓
    1.84
     gratuito
    1.73
     gratis
    1.68
     downloadable
    1.63
     gratuitamente
    1.59
     unlimited
    1.52
     Gratis
    1.48
     postage
    1.47
     gratuits
    1.47
    Activations Density 0.721%

    No Known Activations