© 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. 2204
    Prev
    Next
    INDEX
    Explanations

    asking for more information

    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
     (
    0.95
    (-
    0.92
     (=
    0.91
    (
    0.88
    (!
    0.86
     $(\
    0.82
    ‪
    0.82
     („
    0.81
    ُ
    0.80
    -
    0.77
    POSITIVE LOGITS
     disney
    1.30
     viagra
    1.27
     canada
    1.26
     walmart
    1.26
     australia
    1.25
     casino
    1.24
     france
    1.23
     botao
    1.22
     fiyat
    1.22
     mexico
    1.21
    Activations Density 1.606%

    No Known Activations