© 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. 31-GEMMASCOPE-2-RES-262K
    7. 202108
    Prev
    Next
    INDEX
    Explanations

    peer-to-peer network

    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
    ције
    0.50
    asciiPanel
    0.50
    hart
    0.47
    ด์
    0.44
    डमी
    0.44
    phant
    0.43
    骶
    0.43
    gård
    0.43
    Hawk
    0.42
    splitContainer
    0.42
    POSITIVE LOGITS
     mania
    0.48
     sehingga
    0.46
     clos
    0.46
     prices
    0.46
     rags
    0.46
     veces
    0.45
     gd
    0.44
     impres
    0.44
     chaf
    0.44
    ₨
    0.44
    Activations Density 0.003%

    No Known Activations