© 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. 260569
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     (<
    0.51
     आएंगे
    0.48
     (\<
    0.46
    যোগ্য
    0.46
     shrugged
    0.46
     direção
    0.46
    ObjectURL
    0.46
     rutrum
    0.45
     উদ
    0.45
    <unused34>
    0.45
    POSITIVE LOGITS
    sthe
    0.48
    其
    0.47
    эр
    0.47
    muestra
    0.47
    全部
    0.46
    javax
    0.43
    nt
    0.43
    aser
    0.43
    syllabus
    0.43
    rte
    0.42
    Activations Density 0.000%

    No Known Activations