© 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. 107765
    Prev
    Next
    INDEX
    Explanations

    services solutions

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

    explaining causes and effects

    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
    υ
    0.57
     Spam
    0.52
    ുകളിൽ
    0.50
     versión
    0.48
     Polonia
    0.47
     IFN
    0.47
    িবদ্ধ
    0.47
     Um
    0.47
     isa
    0.46
     was
    0.46
    POSITIVE LOGITS
     فنا
    0.53
    Truly
    0.53
     لاز
    0.52
     भो
    0.47
     فهو
    0.46
     彼
    0.46
     فلا
    0.46
    Encycl
    0.46
    DataBase
    0.46
    Berat
    0.45
    Activations Density 0.000%

    No Known Activations