© 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. 14688
    Prev
    Next
    INDEX
    Explanations

    diagnosis

    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
     lic
    0.68
     Lic
    0.62
     google
    0.60
     불편
    0.56
    */)
    0.54
     Type
    0.53
     LIC
    0.53
     Licence
    0.52
    巡
    0.52
     E
    0.51
    POSITIVE LOGITS
    škai
    0.64
    diagnosis
    0.61
    guid
    0.59
    蓿
    0.59
     wiad
    0.57
    हिनी
    0.57
    iscid
    0.56
     брю
    0.55
    ടിക്ക
    0.55
    जगी
    0.54
    Activations Density 0.000%

    No Known Activations