© 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. 78674
    Prev
    Next
    INDEX
    Explanations

    properties and statistics

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

    Ignoring constants and fluctuations

    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
    #
    0.50
    &
    0.50
    ance
    0.48
    case
    0.46
    azz
    0.46
    ala
    0.45
     be
    0.44
     &
    0.44
    oms
    0.44
    unc
    0.43
    POSITIVE LOGITS
    لین
    0.55
     mladi
    0.54
     sauvegard
    0.52
     benessere
    0.50
    লিন
    0.49
     μεταξύ
    0.49
     klanten
    0.49
    țională
    0.49
    唧
    0.49
    <unused66>
    0.47
    Activations Density 0.002%

    No Known Activations