© 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. 242438
    Prev
    Next
    INDEX
    Explanations

    naming or classification

    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
     have
    0.53
     osoby
    0.52
     draws
    0.52
    ,}
    0.52
     imaju
    0.51
     luch
    0.50
     pulls
    0.50
     nor
    0.50
     vzdu
    0.49
     än
    0.48
    POSITIVE LOGITS
    specified
    0.60
    declared
    0.53
    companies
    0.53
    bank
    0.49
    years
    0.49
    moving
    0.48
    burden
    0.48
    i
    0.48
    名为
    0.48
    fitness
    0.48
    Activations Density 0.000%

    No Known Activations