© 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. 12823
    Prev
    Next
    INDEX
    Explanations

    things or concepts

    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
    ꫝ
    0.57
    Analyser
    0.56
    Roma
    0.55
    buyers
    0.54
    перы
    0.52
    Cage
    0.52
    ETING
    0.51
    zynarod
    0.51
    །
    0.50
    ⌝
    0.50
    POSITIVE LOGITS
     groceries
    0.64
     glycolysis
    0.63
     housework
    0.60
     vehicle
    0.59
     GNP
    0.58
     affect
    0.57
     particle
    0.56
     something
    0.56
     rejuvenate
    0.55
     restocking
    0.55
    Activations Density 0.000%

    No Known Activations