© 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. 256758
    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
    clinical
    0.50
    fourths
    0.49
    叩
    0.47
    蕲
    0.45
    හාර
    0.44
    糖尿
    0.43
    <0x96>
    0.43
    簡易
    0.43
    月初
    0.43
    POSITIVE LOGITS
     שמ
    0.49
    WindowConstants
    0.47
     uranium
    0.45
    ית
    0.43
    ীয়
    0.43
     Πολ
    0.43
     ያስፈል
    0.42
     independ
    0.42
    ాన్
    0.42
     KER
    0.42
    Activations Density 0.000%

    No Known Activations