© 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. 41-GEMMASCOPE-2-RES-262K
    7. 61083
    Prev
    Next
    INDEX
    Explanations

    a short phrase

    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_all/layer_41_width_262k_l0_big
    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
    criptive
    0.45
    秝
    0.41
    سازی
    0.39
    <unused29>
    0.38
    Grunge
    0.37
    注射
    0.37
     वैक्सी
    0.37
    䄳
    0.37
     नक्स
    0.36
    ARRANT
    0.36
    POSITIVE LOGITS
     declaration
    0.44
     cooperative
    0.43
     коопера
    0.42
     மன்ற
    0.41
     협
    0.39
     Ch
    0.39
     его
    0.39
     cooper
    0.38
    ienne
    0.37
     hogs
    0.37
    Activations Density 0.864%

    No Known Activations