© 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. 1361
    Prev
    Next
    INDEX
    Explanations

    like me 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
     elytris
    0.96
    വ്ര
    0.89
    ີ່
    0.89
    䞍
    0.88
     featurenumber
    0.85
     punctato
    0.85
    酭
    0.84
    េទ
    0.84
    parvec
    0.84
    酛
    0.82
    POSITIVE LOGITS
     Toe
    0.66
     also
    0.65
     and
    0.63
     works
    0.60
     or
    0.57
     Works
    0.56
    为大家
    0.56
    磯
    0.56
     Row
    0.55
     Swim
    0.55
    Activations Density 1.109%

    No Known Activations