© 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. 256535
    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
    anguage
    0.52
    antiene
    0.47
     ars
    0.47
    题
    0.46
    题目
    0.46
    ربون
    0.46
    วันนี้
    0.45
    Literatura
    0.45
     kesempatan
    0.45
    eca
    0.45
    POSITIVE LOGITS
    zieh
    0.48
     υ
    0.43
    chny
    0.43
     모습을
    0.42
     Рі
    0.41
    妥
    0.41
     hypoxic
    0.41
     royalties
    0.40
     tots
    0.40
     lakhs
    0.40
    Activations Density 0.000%

    No Known Activations