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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15805
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
     STEM
    0.57
    Theta
    0.52
     Roche
    0.52
    ાડ
    0.52
     theta
    0.50
    ၌
    0.50
    ulae
    0.49
    膜
    0.49
    DbType
    0.48
    Roth
    0.48
    POSITIVE LOGITS
     लीवर
    0.65
    ιν
    0.63
    ক্ত
    0.63
     Appet
    0.61
    ésus
    0.61
     ordenada
    0.59
    茜
    0.57
     Looking
    0.57
     প্রক্রিয়া
    0.57
     vin
    0.55
    Activations Density 0.000%

    No Known Activations