© 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. 228922
    Prev
    Next
    INDEX
    Explanations

    book Steve

    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
     отече
    0.49
     apoyo
    0.49
     berarti
    0.48
     höchsten
    0.48
     ago
    0.45
     loo
    0.45
    侃
    0.45
    त्रेयी
    0.44
     либо
    0.44
     graces
    0.43
    POSITIVE LOGITS
    datad
    0.52
    jon
    0.48
    rowadz
    0.48
    urs
    0.47
                   
    0.46
    ob
    0.46
    egen
    0.46
    ungle
    0.46
    سٹر
    0.46
    jud
    0.46
    Activations Density 0.000%

    No Known Activations