© 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. 113350
    Prev
    Next
    INDEX
    Explanations

    established guidelines

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

    implementation, writing, evaluation, criteria

    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
    ри
    0.52
    newValue
    0.50
    ubishi
    0.49
    ukiyoe
    0.48
    ৬
    0.47
    stvu
    0.46
    飲む
    0.46
     সমাজ
    0.46
    ⛲
    0.46
    displayed
    0.45
    POSITIVE LOGITS
     остальных
    0.54
     datasheet
    0.49
     Pareto
    0.47
     Criteria
    0.47
     conversation
    0.46
     Agreement
    0.45
     office
    0.45
     resto
    0.45
     बाकी
    0.45
     todas
    0.45
    Activations Density 0.004%

    No Known Activations