© 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. 114969
    Prev
    Next
    INDEX
    Explanations

    status or condition

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

    computer vision

    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
    ຊ
    0.51
    大
    0.49
    ス
    0.48
    возмо
    0.47
    共产
    0.46
    وبي
    0.46
    es
    0.46
    屋内
    0.46
    小
    0.45
    カラー
    0.45
    POSITIVE LOGITS
     vín
    0.47
     doigts
    0.47
     susc
    0.46
    blers
    0.46
     hermano
    0.46
     สิ่ง
    0.44
     syd
    0.43
     trypt
    0.43
    sellers
    0.43
     mascul
    0.42
    Activations Density 0.000%

    No Known Activations