© 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. 98021
    Prev
    Next
    INDEX
    Explanations

    celebrating anniversaries or awards

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

    terms, explanations, and receipts

    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
     hepinize
    0.48
    tos
    0.46
     voulez
    0.46
     svim
    0.46
     continuando
    0.45
    ኳ
    0.45
     vouloir
    0.44
     therefor
    0.43
    ⌦
    0.43
    워크
    0.43
    POSITIVE LOGITS
     चिह्न
    0.44
     özellik
    0.44
     প্রকাশের
    0.43
     আকারে
    0.43
     অত্যা
    0.42
    ১৮
    0.42
     বৈশিষ্ট
    0.42
     i
    0.41
     বছরের
    0.41
     مقامات
    0.40
    Activations Density 0.005%

    No Known Activations