© 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. 7714
    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
    และ
    0.28
    C
    0.27
     Women
    0.27
     Housewives
    0.27
    ৬
    0.27
     Jackson
    0.26
    0.26
    E
    0.26
     Breast
    0.26
     Avengers
    0.26
    POSITIVE LOGITS
     to
    0.33
     direto
    0.32
     nisid
    0.31
     utilisateurs
    0.30
     algebras
    0.30
     ativos
    0.30
     vertices
    0.30
     utilice
    0.29
     associa
    0.29
     videomuz
    0.29
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.