© 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. 13500
    Prev
    Next
    INDEX
    Explanations

    open source project

    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
     Restart
    0.63
    ότη
    0.62
     живот
    0.59
    ılarak
    0.55
    ($(
    0.54
     –,
    0.54
     Iw
    0.53
    anger
    0.53
     uncl
    0.53
    arter
    0.52
    POSITIVE LOGITS
    UserService
    0.59
    }^\
    0.55
     Пользова
    0.55
    ).^
    0.54
    Pid
    0.52
    userId
    0.52
    UserController
    0.52
    izdat
    0.51
    Ци
    0.50
     देनी
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.