© 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. 13121
    Prev
    Next
    INDEX
    Explanations

    introduction headings

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

    introduction: followed by number or title

    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
     estará
    0.64
    8
    0.63
     vede
    0.60
     serão
    0.59
     terá
    0.59
     môžu
    0.58
     kaynağından
    0.58
     irá
    0.57
     será
    0.56
     seront
    0.56
    POSITIVE LOGITS
    introduction
    0.71
    to
    0.71
     INTRODUCTION
    0.68
    Introduction
    0.66
    ductory
    0.62
    으
    0.61
    as
    0.61
     Introduction
    0.59
    i
    0.59
     introduction
    0.58
    Activations Density 0.009%

    No Known Activations