© 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. 258290
    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
     چھوٹ
    0.54
    覚えて
    0.52
    מין
    0.52
     자동차
    0.50
     comprador
    0.48
    鄯
    0.47
     топли
    0.47
     PROP
    0.47
    늄
    0.46
     costru
    0.46
    POSITIVE LOGITS
    seven
    0.53
    eight
    0.49
    an
    0.45
    related
    0.44
    unlock
    0.44
    possible
    0.44
    introduction
    0.44
    win
    0.43
    wow
    0.43
    three
    0.43
    Activations Density 0.000%

    No Known Activations