© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1027
    Prev
    Next
    INDEX
    Explanations

    main method arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    ىسى
    0.52
    motor
    0.50
     nascent
    0.50
    organic
    0.49
    chlor
    0.49
     nello
    0.48
    Ꮮ
    0.48
    奔驰
    0.47
    \`
    0.47
    週期
    0.46
    POSITIVE LOGITS
     LayoutInflater
    0.58
     Conte
    0.57
     Diskussion
    0.57
     Nothing
    0.56
     Consultado
    0.56
     Congratulations
    0.55
     Fark
    0.54
     Campos
    0.54
     Sebuah
    0.53
     Karena
    0.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.