© 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. 28249
    Prev
    Next
    INDEX
    Explanations

    legal, trade, or specific foreign words

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

    numbered list items

    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
    ığını
    0.52
    处置
    0.45
     設計
    0.44
     जुड़ी
    0.44
     ±
    0.43
     رسمي
    0.43
     radicales
    0.43
    荩
    0.43
    кса
    0.42
    PARTMENT
    0.42
    POSITIVE LOGITS
     perdagangan
    0.50
     ክብ
    0.50
    moor
    0.48
     ص
    0.47
    wert
    0.47
     comercio
    0.46
     prosecute
    0.46
    භ
    0.45
     morn
    0.44
    prend
    0.44
    Activations Density 0.001%

    No Known Activations