© 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. 14204
    Prev
    Next
    INDEX
    Explanations

    technical or specific information

    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
     Systems
    0.62
     นะ
    0.60
     SYSTEMS
    0.60
    argas
    0.56
    Fu
    0.55
     ਵਿੱਚ
    0.55
    ふ
    0.55
    Systems
    0.55
    ($
    0.55
    ych
    0.55
    POSITIVE LOGITS
     palab
    0.54
     shew
    0.54
     extrapolate
    0.53
     రాయ
    0.52
    abee
    0.52
     Кра
    0.52
     perp
    0.52
    館
    0.52
    又要
    0.52
    Rated
    0.51
    Activations Density 0.000%

    No Known Activations