© 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. 254503
    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
    all
    0.57
    el
    0.50
    get
    0.49
     ONLINE
    0.49
    ad
    0.48
    Gt
    0.47
    adde
    0.47
    T
    0.46
    Run
    0.45
    adó
    0.45
    POSITIVE LOGITS
    ھے
    0.51
     Bakan
    0.48
     松
    0.47
     biv
    0.47
     dragState
    0.47
     vardı
    0.45
     functors
    0.45
    殳
    0.45
     ва
    0.44
    ヒル
    0.44
    Activations Density 0.000%

    No Known Activations