© 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. 1089
    Prev
    Next
    INDEX
    Explanations

    organizations and resources

    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
     (
    1.73
     tons
    1.63
     没有
    1.62
     Phúc
    1.61
     less
    1.59
     Uy
    1.58
     still
    1.55
     reduce
    1.54
     Χ
    1.53
     separate
    1.53
    POSITIVE LOGITS
    alex
    2.29
    aprend
    2.06
    english
    1.96
    adinam
    1.89
    avila
    1.88
    america
    1.87
    esehatan
    1.87
    japan
    1.87
    utilizzo
    1.86
    osw
    1.85
    Activations Density 0.688%

    No Known Activations