© 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. 138720
    Prev
    Next
    INDEX
    Explanations

    future prospect

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

    economic leakage and reparations

    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
     ብዙውን
    0.53
    {
    0.49
    <0x80>
    0.48
    ta
    0.47
    *{-
    0.47
    înes
    0.44
    én
    0.43
    features
    0.42
    육
    0.42
     يوجد
    0.42
    POSITIVE LOGITS
     suara
    0.54
     kole
    0.54
     miliar
    0.51
     agreg
    0.49
     navegador
    0.49
     rendu
    0.49
    Ꮈ
    0.48
     Kole
    0.47
     sociétés
    0.47
     Serikat
    0.47
    Activations Density 0.000%

    No Known Activations