© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1667
    Prev
    Next
    INDEX
    Explanations

    purpose, context, cause, function

    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_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
    evsky
    1.33
    读取
    1.31
     뭐
    1.27
     idk
    1.26
    你不
    1.24
     아무
    1.22
    妳
    1.18
    我覺得
    1.17
     읽
    1.16
    覺得
    1.16
    POSITIVE LOGITS
     tipos
    1.11
     soorten
    1.06
     moyens
    1.03
    となる
    1.02
     tipo
    1.00
     kinds
    1.00
     sorts
    0.97
     constitutes
    0.97
     types
    0.95
     avenir
    0.95
    Activations Density 0.635%

    No Known Activations