© 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. 53-GEMMASCOPE-2-RES-262K
    7. 64519
    Prev
    Next
    INDEX
    Explanations

    cel followed by onis, shading, or cious

    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_53_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
    aug
    0.49
     aug
    0.38
    urnal
    0.36
    ི་
    0.36
    並
    0.36
    ale
    0.36
    вле
    0.36
    ags
    0.35
    ilk
    0.35
    最
    0.35
    POSITIVE LOGITS
    ibat
    0.45
     المس
    0.42
    olet
    0.41
     disconnecting
    0.41
    MSP
    0.40
     puțin
    0.39
    cích
    0.39
    डक
    0.38
     الأوروب
    0.38
     starved
    0.38
    Activations Density 0.001%

    No Known Activations