© 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. 259090
    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
    льны
    0.41
    箫
    0.41
    вари
    0.41
    贱
    0.41
    нов
    0.40
    ච්
    0.40
    ров
    0.40
    лам
    0.39
    вае
    0.39
    া
    0.39
    POSITIVE LOGITS
     porridge
    0.46
     bison
    0.45
     Pils
    0.43
    নিবার
    0.43
     Opus
    0.43
    IdentityProvider
    0.42
     hazelnuts
    0.42
     granola
    0.42
     Luton
    0.42
     susu
    0.42
    Activations Density 0.000%

    No Known Activations