© 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. 30902
    Prev
    Next
    INDEX
    Explanations

    mention each customer

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

    about specific topics or instructions

    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
    ck
    0.52
    ứng
    0.47
    bee
    0.46
     ジュ
    0.46
    サンプル
    0.46
    termin
    0.46
    𝚍
    0.46
     രാഷ്ട്ര
    0.46
    adays
    0.45
    gaz
    0.45
    POSITIVE LOGITS
    ائص
    0.47
     Store
    0.46
     Booklet
    0.43
     کرنے
    0.43
    讲
    0.41
    の子
    0.41
     للق
    0.41
     to
    0.41
     również
    0.41
    จากการ
    0.41
    Activations Density 0.000%

    No Known Activations