© 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. 254618
    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
    拵
    0.58
    掣
    0.49
    Pog
    0.48
    剞
    0.48
    َنْ
    0.47
    恣
    0.47
    絞
    0.46
    嗔
    0.46
    フィ
    0.46
    予防
    0.46
    POSITIVE LOGITS
     レザー
    0.48
     continúa
    0.48
     ハン
    0.48
     laborers
    0.48
    ി
    0.46
     placeholders
    0.46
    ługa
    0.45
    არ
    0.45
     servo
    0.44
    ারন
    0.44
    Activations Density 0.001%

    No Known Activations