© 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. 13608
    Prev
    Next
    INDEX
    Explanations

    Administrator access

    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
     المب
    0.56
     MF
    0.54
    采
    0.53
    কাত
    0.52
     మారింది
    0.51
    MF
    0.50
    Γ
    0.50
    कुल
    0.50
    Pods
    0.49
    🩹
    0.49
    POSITIVE LOGITS
     Aaj
    0.61
     illo
    0.60
     pribli
    0.57
     illuminate
    0.57
     memang
    0.55
     Certains
    0.55
     prive
    0.55
     domani
    0.55
     निवास
    0.55
     Produto
    0.55
    Activations Density 0.000%

    No Known Activations