© 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. 151657
    Prev
    Next
    INDEX
    Explanations

    financial terms or descriptions

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

    full stack developer

    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
     дори
    0.45
     отли
    0.44
     省
    0.44
     スタッドレスタイヤ
    0.43
    үл
    0.42
    alarında
    0.42
     ભાગ
    0.42
     كلمات
    0.41
    EEN
    0.41
    校园
    0.40
    POSITIVE LOGITS
     dedo
    0.50
    ‌های
    0.48
     در
    0.47
     puis
    0.46
    の
    0.46
     utiliser
    0.45
     savvy
    0.44
     SWAT
    0.44
    ‌ترین
    0.44
    article
    0.44
    Activations Density 0.001%

    No Known Activations