© 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. 24264
    Prev
    Next
    INDEX
    Explanations

    vertical slice, integration, farming, aerospace

    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
    <unused25>
    0.45
     مربع
    0.43
    orant
    0.43
    гент
    0.41
    大的
    0.41
     CryptoJS
    0.40
    ^{*}=\
    0.40
    ्यर
    0.40
     عملية
    0.40
     க
    0.39
    POSITIVE LOGITS
     Vertical
    0.91
     vertical
    0.85
    Vertical
    0.80
     вертика
    0.78
    vertical
    0.77
     verticales
    0.71
     verticale
    0.65
     Vert
    0.64
     vert
    0.63
     Horizontal
    0.63
    Activations Density 0.004%

    No Known Activations