© 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. 13526
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    Ve
    0.57
    Q
    0.57
    Kh
    0.55
    Aj
    0.54
    <code>
    0.54
    Chris
    0.54
    Personally
    0.54
    q
    0.54
    Inform
    0.54
    Zombie
    0.53
    POSITIVE LOGITS
     Nantucket
    0.72
     Tulane
    0.70
     Jalisco
    0.67
     उत्तराखंड
    0.66
     throwback
    0.66
    veston
    0.65
     wel
    0.64
     wt
    0.64
     Galveston
    0.64
     old
    0.63
    Activations Density 0.003%

    No Known Activations