© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 27602
    Prev
    Next
    INDEX
    Explanations

    top ten percent

    np_acts-logits-general · gemini-2.5-flash-lite

    ranking and popularity

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     cells
    0.45
    ائم
    0.44
     revelar
    0.44
    を加
    0.43
     capsules
    0.43
    ండే
    0.42
     expressão
    0.41
    本
    0.41
     agregar
    0.40
     capsule
    0.39
    POSITIVE LOGITS
     недалеко
    0.54
     arrivée
    0.49
     назем
    0.48
    ską
    0.48
    determination
    0.48
    niej
    0.47
    🚣
    0.47
    overline
    0.47
    gig
    0.46
     过
    0.46
    Activations Density 0.000%

    No Known Activations