© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 245983
    Prev
    Next
    INDEX
    Explanations

    Corvette Sting, customer service, singing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    褔
    0.57
     क्षतिग्रस्त
    0.52
    reated
    0.51
    ína
    0.49
    缫
    0.49
    fibr
    0.48
    ManagerPortal
    0.48
    werken
    0.48
    孢
    0.47
     المرأة
    0.47
    POSITIVE LOGITS
    W
    0.49
     Lear
    0.49
    ભાવ
    0.47
     justific
    0.46
    AL
    0.46
    quele
    0.46
     Thy
    0.44
     Kapil
    0.43
    L
    0.43
     thy
    0.43
    Activations Density 0.000%

    No Known Activations