© 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. 375
    Prev
    Next
    INDEX
    Explanations

    information manuals and strategies

    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
     AMOUNT
    1.17
     해당
    1.16
     изначально
    1.07
    ดังกล่าว
    1.00
    😔
    0.99
    称
    0.97
    任意の
    0.97
    下記の
    0.97
    🥺
    0.95
     😉
    0.95
    POSITIVE LOGITS
     Handbook
    1.76
     handbook
    1.59
    Handbook
    1.56
     Essays
    1.54
     Perspectives
    1.52
     Revisited
    1.50
     Principles
    1.47
     Adventures
    1.47
     Routledge
    1.44
     Lectures
    1.43
    Activations Density 1.141%

    No Known Activations