© 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. 13079
    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
    0.78
     and
    0.71
    .
    0.70
    ;
    0.69
      
    0.65
    ,
    0.65
    <eos>
    0.63
    ↵↵
    0.63
    ↵
    0.62
     on
    0.62
    POSITIVE LOGITS
    RuL
    0.68
     Bhagavato
    0.64
    ępuje
    0.63
    attho
    0.63
    sächlich
    0.63
     থাকিলেও
    0.62
     হইতেছে
    0.61
    dDays
    0.61
    PAAm
    0.60
     QuantityOnHand
    0.59
    Activations Density 0.000%

    No Known Activations