© 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. 260375
    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
    ométrique
    0.51
    ιε
    0.47
     chạm
    0.46
    ┅
    0.46
    젓
    0.46
     gồm
    0.44
     théorème
    0.44
     চালানোর
    0.43
    ιο
    0.43
    ief
    0.43
    POSITIVE LOGITS
     माइक्रो
    0.47
     శాతం
    0.46
     ኩ
    0.46
     සී
    0.44
     따른
    0.44
     சி
    0.44
    ovid
    0.43
     가장
    0.43
     axonal
    0.42
     matters
    0.42
    Activations Density 0.001%

    No Known Activations