© 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. 257700
    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
     injurious
    0.50
     pacing
    0.49
     ENGINEERING
    0.49
     bathroom
    0.48
    짊
    0.48
    ኘት
    0.47
    ॉर्डिंग
    0.47
    ારીખ
    0.47
    泞
    0.47
     polynomial
    0.47
    POSITIVE LOGITS
    t
    0.57
    ktor
    0.57
    ica
    0.49
    the
    0.48
    vat
    0.47
    tahun
    0.47
    xd
    0.46
    6
    0.46
    ka
    0.46
    ino
    0.46
    Activations Density 0.000%

    No Known Activations