© 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. 33640
    Prev
    Next
    INDEX
    Explanations

    the story / Bernard / methodologies / oriented

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

    topic context question

    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
     redeeming
    0.48
     registró
    0.45
     প্রশাসন
    0.45
    ให้บริการ
    0.43
     bulunduğu
    0.43
     retailing
    0.43
    虧
    0.43
     hende
    0.42
    謠
    0.42
     প্রার্থনা
    0.42
    POSITIVE LOGITS
    ஜா
    0.52
    ستگی
    0.41
    даго
    0.40
     tarn
    0.40
     ­
    0.40
    <unused1008>
    0.40
     maximally
    0.39
     стре
    0.39
     conclusively
    0.39
     тон
    0.38
    Activations Density 0.001%

    No Known Activations