© 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. 165863
    Prev
    Next
    INDEX
    Explanations

    ultimate guide, good revenue, great revenue, surprised at, biological manufacturing

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

    market driven

    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
    ，“
    0.44
     journeys
    0.44
    目で
    0.43
     inputArray
    0.43
     igjen
    0.43
    躏
    0.43
     tendría
    0.42
    。...
    0.42
     moduli
    0.41
    ।-
    0.41
    POSITIVE LOGITS
    im
    0.63
    >
    0.62
    il
    0.59
    id
    0.57
    스
    0.55
    <
    0.54
    ôn
    0.52
    را
    0.51
    %
    0.51
    ্স
    0.49
    Activations Density 0.001%

    No Known Activations