© 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. 14367
    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
     públicos
    0.52
    シャ
    0.41
     piloted
    0.41
    珠
    0.41
     público
    0.40
     কর্মকর্তা
    0.40
     pubblico
    0.40
     pubblici
    0.39
    คู่
    0.38
    rar
    0.38
    POSITIVE LOGITS
    𝓜
    0.46
    爫
    0.45
    ymethyl
    0.44
    leştir
    0.44
     Mathematical
    0.43
    iedenis
    0.43
     Whittaker
    0.43
    𝖘
    0.43
    ાન
    0.42
    lund
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.