© 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. 254279
    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
     privile
    0.47
     embodied
    0.45
    成为
    0.45
    休闲
    0.42
     Fors
    0.41
     अभिव्य
    0.41
    
    0.41
    的行为
    0.41
    Fors
    0.41
     devenir
    0.40
    POSITIVE LOGITS
    ಸ್ಕ
    0.48
    ନ୍ଦ
    0.44
    vaient
    0.43
    聽到
    0.43
    手間
    0.43
     noirâtres
    0.43
     инстру
    0.42
     ଜ
    0.42
     manometer
    0.42
    陖
    0.42
    Activations Density 0.000%

    No Known Activations