© 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. 254862
    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
     fís
    0.54
    טית
    0.53
    ارين
    0.51
    クス
    0.50
    четов
    0.49
    其
    0.47
     conducción
    0.47
    襁
    0.46
    市民
    0.46
    رین
    0.46
    POSITIVE LOGITS
    an
    0.57
    kar
    0.55
    ke
    0.54
    wit
    0.54
    man
    0.53
    ka
    0.52
    ame
    0.52
    ond
    0.52
    way
    0.49
    ont
    0.49
    Activations Density 0.000%

    No Known Activations