© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79070
    Prev
    Next
    INDEX
    Explanations

    Bitcoin and Chinese text

    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_262k_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
    Evil
    0.49
    <0xB7>
    0.45
    evil
    0.45
    ла
    0.44
     ",
    0.42
    ั่ง
    0.41
     asiento
    0.41
    Static
    0.40
    ╧
    0.40
    ̸
    0.40
    POSITIVE LOGITS
    有点
    0.50
     relativement
    0.48
     مدارس
    0.45
     داشتن
    0.44
     अपेक्षाकृत
    0.44
    萱
    0.44
    䈤
    0.43
    蕗
    0.43
     advertis
    0.43
    的设计
    0.43
    Activations Density 0.003%

    No Known Activations