© 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. 131524
    Prev
    Next
    INDEX
    Explanations

    text hyperlinks for informational

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

    introductions and descriptions

    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
    ިއ
    0.54
     parce
    0.48
    鳗
    0.48
    মান
    0.47
    ката
    0.46
    ラボ
    0.46
    Л
    0.46
    $("
    0.46
    src
    0.45
    icheskoj
    0.45
    POSITIVE LOGITS
     लची
    0.44
     enrolment
    0.44
     Answers
    0.43
     pensée
    0.42
     basing
    0.41
     consent
    0.41
     GAM
    0.41
     potente
    0.41
     সম্মতি
    0.41
     cxd
    0.40
    Activations Density 0.001%

    No Known Activations