© 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
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 13368
    Prev
    Next
    INDEX
    Explanations

    code comments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
    -"+
    0.60
    ");</
    0.60
     ……………………
    0.59
    …………………………………………
    0.59
    :");
    0.57
    .\"
    0.57
    :\
    0.57
    ATIONS
    0.57
     следующих
    0.57
    orial
    0.56
    POSITIVE LOGITS
     noqa
    1.37
     <--
    1.29
    注意
    1.24
    相当于
    1.23
     avoids
    1.20
    gives
    1.14
     이게
    1.05
     avoid
    1.03
    because
    1.03
    same
    1.03
    Activations Density 0.005%

    No Known Activations