© 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. 6945
    Prev
    Next
    INDEX
    Explanations

    numbers after symbols

    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
    ូន
    0.47
    ួក
    0.46
    ُو
    0.46
     permeability
    0.46
     geometrically
    0.44
    routingHeader
    0.43
    <unused967>
    0.43
    ័
    0.43
     servicing
    0.43
    াত্মক
    0.42
    POSITIVE LOGITS
    1
    0.53
     Journalist
    0.46
    in
    0.45
     Museum
    0.43
     Restaur
    0.43
    8
    0.41
     Expedia
    0.41
     Repub
    0.40
     Forum
    0.40
     Plaza
    0.40
    Activations Density 0.047%

    No Known Activations