© 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. 255687
    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
    依靠
    0.48
    咐
    0.47
    睿
    0.44
    认知
    0.44
    𝑡
    0.44
    ﺩ
    0.43
    <0x04>
    0.42
     humility
    0.42
    戛
    0.42
    ِس
    0.41
    POSITIVE LOGITS
     chuyên
    0.45
    र्घ
    0.43
     tranh
    0.43
     MeOH
    0.42
    ť
    0.42
     mø
    0.42
     FRESH
    0.42
     vært
    0.42
     厚
    0.42
     обеспечить
    0.42
    Activations Density 0.000%

    No Known Activations