© 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. 245343
    Prev
    Next
    INDEX
    Explanations

    jobs, manufacturers, artists

    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
    ک
    0.75
    ر
    0.71
    ب
    0.68
    ی
    0.67
    م
    0.63
    هم
    0.62
    У
    0.58
    ز
    0.56
    ش
    0.54
    을
    0.53
    POSITIVE LOGITS
     lays
    0.52
     Wilbur
    0.52
     vzděl
    0.50
    ্ডি
    0.50
    াস্থ্য
    0.49
     Wil
    0.49
     argue
    0.48
     ဖ
    0.48
     熱
    0.47
     Cull
    0.47
    Activations Density 0.000%

    No Known Activations