© 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. 215
    Prev
    Next
    INDEX
    Explanations

    lists and definitions

    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
     Large
    1.10
     U
    1.01
     Χ
    0.99
     小型
    0.99
     large
    0.88
     FY
    0.87
     ’
    0.86
     u
    0.86
     S
    0.86
     R
    0.85
    POSITIVE LOGITS
    that
    1.21
    driven
    1.16
    dengan
    1.14
    handlebars
    1.14
    ukiyoe
    1.13
    across
    1.10
    pokemon
    1.10
    scre
    1.10
    webhook
    1.09
    ambient
    1.07
    Activations Density 0.155%

    No Known Activations