Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 3971
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     おい
    1.61
     ҷ
    1.53
    おい
    1.42
    中毒
    1.39
     로그인
    1.37
    汥
    1.33
     仕様
    1.33
    虻
    1.31
    CLASSI
    1.31
    すでに
    1.29
    POSITIVE LOGITS
     poprzez
    1.22
     through
    1.21
     via
    1.20
    ,
    1.14
     melalui
    1.09
     عبر
    1.04
     also
    1.03
     tramite
    1.00
     através
    0.99
     encompassing
    0.99
    Activations Density 0.000%

    No Known Activations