© 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. 30384
    Prev
    Next
    INDEX
    Explanations

    various languages and content

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

    business and investment details

    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
    only
    0.45
     மட்டுமே
    0.45
    aden
    0.45
     فقط
    0.45
    ata
    0.43
    只
    0.43
    全
    0.43
     only
    0.42
    can
    0.42
    aschen
    0.42
    POSITIVE LOGITS
    ంబేద్కర్
    0.48
    ูนย์
    0.42
    িকারী
    0.42
     onError
    0.40
     የአ
    0.40
     kaçtır
    0.40
    Կ
    0.40
    ینگ
    0.39
     kullanıcı
    0.39
     اجرای
    0.39
    Activations Density 0.000%

    No Known Activations