© 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. 13630
    Prev
    Next
    INDEX
    Explanations

    creative

    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
    boldsymbol
    0.68
    ^{*}}
    0.68
    *{-
    0.61
    >${
    0.58
     mathbf
    0.58
    varphi
    0.56
    fancy
    0.56
     }
    0.55
    }\,
    0.55
    Dirac
    0.55
    POSITIVE LOGITS
     outpost
    0.70
     reinvigor
    0.69
     invigor
    0.68
     inclement
    0.66
     impromptu
    0.65
     cashback
    0.64
     inevitable
    0.63
     remorse
    0.63
     vesting
    0.63
     acquies
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.