© 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. 41-GEMMASCOPE-2-RES-262K
    7. 8957
    Prev
    Next
    INDEX
    Explanations

    enameling, scale armor, hidden state, drawing

    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
    ナソニック
    0.61
    <unused99>
    0.59
     ด่า
    0.57
    streetlight
    0.57
    んにちは
    0.56
    лянчук
    0.55
     analý
    0.55
    𝗂
    0.55
    ោម
    0.55
     Maddie
    0.55
    POSITIVE LOGITS
     Museum
    0.81
     sculptural
    0.78
     Mughal
    0.77
     decorative
    0.76
     Medici
    0.75
    髹
    0.75
     polych
    0.73
     Florent
    0.73
     inlay
    0.73
     Decoration
    0.69
    Activations Density 0.013%

    No Known Activations