© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6506
    Prev
    Next
    INDEX
    Explanations

    citations and verses

    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_31_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
    <unused328>
    0.50
    رداری
    0.47
    <unused475>
    0.47
    UAGE
    0.46
    <unused671>
    0.46
     nových
    0.46
    FreeBuf
    0.45
    <unused389>
    0.44
    کومت
    0.44
    <unused406>
    0.44
    POSITIVE LOGITS
    1
    0.68
    2
    0.56
     #
    0.53
    3
    0.51
     III
    0.50
    １
    0.49
    4
    0.48
    0.47
     th
    0.45
    5
    0.44
    Activations Density 0.048%

    No Known Activations