© 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. 13259
    Prev
    Next
    INDEX
    Explanations

    AI models and 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
    嘅
    0.58
    <unused12>
    0.52
    <unused29>
    0.48
     MDLVertex
    0.48
    <unused48>
    0.47
     என்னுடைய
    0.47
     solchen
    0.46
     solche
    0.46
    다라고
    0.46
    <unused56>
    0.46
    POSITIVE LOGITS
     whose
    0.78
     (!)
    0.75
     (!
    0.73
    whose
    0.71
     whom
    0.69
    (!
    0.65
     among
    0.64
    (!)
    0.64
     despite
    0.63
     amid
    0.61
    Activations Density 0.110%

    No Known Activations