© 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. 146374
    Prev
    Next
    INDEX
    Explanations

    to precede or follow certain words

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

    specific explanations and summaries

    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
     脱
    0.52
     文化
    0.48
     危
    0.47
     kultury
    0.47
     unconditionally
    0.46
     pleinement
    0.46
     inherit
    0.46
     permanently
    0.45
     volontà
    0.45
     含
    0.45
    POSITIVE LOGITS
    to
    0.57
    skateboard
    0.56
    th
    0.54
    sketch
    0.53
    кати
    0.50
    picked
    0.48
    वियस
    0.47
    producer
    0.47
    гами
    0.47
    quiao
    0.46
    Activations Density 0.000%

    No Known Activations