© 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. 235920
    Prev
    Next
    INDEX
    Explanations

    systems administration

    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
    페이지
    0.53
     লঙ্ঘন
    0.50
    री
    0.50
     خی
    0.49
    ২৯
    0.48
     महानगर
    0.48
     בית
    0.47
    ೯
    0.47
     Coconut
    0.46
     ลักษณะ
    0.46
    POSITIVE LOGITS
     كامل
    0.47
    كامل
    0.42
    barra
    0.42
     draft
    0.41
     centrale
    0.41
     ubiquitin
    0.41
     draw
    0.40
     amin
    0.40
    ර්ධ
    0.40
     semic
    0.40
    Activations Density 0.000%

    No Known Activations