© 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. 14540
    Prev
    Next
    INDEX
    Explanations

    images and photographs

    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
     painter
    0.60
     Painter
    0.57
     Picasso
    0.56
    Painter
    0.55
     painters
    0.54
     pictured
    0.53
    '%
    0.53
     Figures
    0.52
     conservatively
    0.52
     Paine
    0.52
    POSITIVE LOGITS
    städter
    0.55
    memiş
    0.55
     měla
    0.54
     snapshot
    0.54
     quốc
    0.54
    ങ്ങ്
    0.54
    photon
    0.53
    riram
    0.53
    haram
    0.53
    酚
    0.53
    Activations Density 0.000%

    No Known Activations