© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13537
    Prev
    Next
    INDEX
    Explanations

    \Method used: 1

    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
    newtheorem
    0.71
    textwidth
    0.69
    '=>'','
    0.62
    borderwidth
    0.59
    strptime
    0.59
    newpage
    0.57
    text
    0.55
    theta
    0.55
    pendown
    0.55
    紋
    0.55
    POSITIVE LOGITS
     LET
    0.79
     let
    0.74
     Jeep
    0.74
     microbiota
    0.69
     Let
    0.68
     Masai
    0.67
     acronym
    0.66
     Kongo
    0.64
     sukses
    0.64
     กม
    0.64
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.