© 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. 86688
    Prev
    Next
    INDEX
    Explanations

    multilingual content and specific vocabulary

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

    examples of phrases or sentences, often with punctuation

    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
     culminated
    0.46
     முதலிய
    0.46
    渾
    0.45
    頗
    0.45
     த
    0.45
     mutagenesis
    0.44
     உட்பட
    0.44
     capricious
    0.44
    immutable
    0.44
    *,
    0.42
    POSITIVE LOGITS
    כים
    0.46
     Guns
    0.46
    嗬
    0.46
     réellement
    0.45
     odmah
    0.45
    pageControl
    0.45
     Америки
    0.44
    乡村
    0.43
    उथ
    0.43
     rychle
    0.43
    Activations Density 0.002%

    No Known Activations