© 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. 70348
    Prev
    Next
    INDEX
    Explanations

    using custom filters

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

    using different methods

    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
    別人
    0.42
     (
    0.40
     umfasst
    0.40
    kills
    0.40
    رو
    0.40
     selben
    0.39
     heparin
    0.38
     hundert
    0.38
     نها
    0.37
     dinyatakan
    0.37
    POSITIVE LOGITS
     Федера
    0.43
     싸
    0.41
     सिंपली
    0.40
     스포츠
    0.39
     공유
    0.38
     మాన
    0.38
     維
    0.37
     공동
    0.37
     Belvedere
    0.37
     পশ্চিম
    0.37
    Activations Density 0.003%

    No Known Activations