© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15604
    Prev
    Next
    INDEX
    Explanations

    read and understand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ευ
    0.42
    ³/
    0.38
     esistono
    0.38
    🏪
    0.37
    przy
    0.37
    בית
    0.36
    ज़ी
    0.36
     ország
    0.36
     purified
    0.35
    ეფ
    0.35
    POSITIVE LOGITS
    を読む
    0.71
     читать
    0.70
     읽
    0.70
     read
    0.68
    อ่าน
    0.64
     bookmark
    0.63
     reading
    0.61
     مهم
    0.61
    看完
    0.61
     прочита
    0.59
    Activations Density 0.184%

    No Known Activations