© 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. 13646
    Prev
    Next
    INDEX
    Explanations

    Home

    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
     turf
    0.58
    現象
    0.54
     ചെയ്യുന്നത്
    0.54
    ptidase
    0.53
     BLUEN
    0.53
    পি
    0.52
    ♬
    0.51
    indazol
    0.50
     кул
    0.50
     digs
    0.49
    POSITIVE LOGITS
     Instead
    0.63
     Again
    0.61
    лега
    0.58
    Goods
    0.56
    ე
    0.56
     ABOUT
    0.55
     Delivered
    0.55
     Goods
    0.54
    aris
    0.54
     about
    0.53
    Activations Density 0.029%

    No Known Activations