© 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. 19575
    Prev
    Next
    INDEX
    Explanations

    PDF files and access instructions

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

    history, genetic, text, objects

    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
     chois
    0.46
    也会
    0.46
    ウエスト
    0.46
     trident
    0.45
    也會
    0.43
    おすすめです
    0.43
     optio
    0.42
    助
    0.41
    ivating
    0.40
     lille
    0.40
    POSITIVE LOGITS
     વિદ્યાર્થી
    0.45
     Кри
    0.45
     সম্পাদিত
    0.44
     Ș
    0.43
     கருத்து
    0.43
     Hacer
    0.43
     Comercial
    0.43
    🎓
    0.42
     memoria
    0.42
     perju
    0.42
    Activations Density 0.000%

    No Known Activations