© 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. 258275
    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
    мера
    0.47
     شاف
    0.45
    ativo
    0.44
    нера
    0.44
    鏟
    0.44
     विवा
    0.44
    譎
    0.43
     género
    0.43
     herm
    0.42
    鐫
    0.42
    POSITIVE LOGITS
     Nasıl
    0.58
     Hart
    0.53
    LM
    0.53
     तेज़
    0.52
     Kast
    0.50
    HOW
    0.50
    REM
    0.49
     Allison
    0.48
     ಉತ್
    0.47
    PUBLIC
    0.47
    Activations Density 0.001%

    No Known Activations