© 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. 20457
    Prev
    Next
    INDEX
    Explanations

    code structures

    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
    ruari
    0.41
    时代
    0.39
    時代
    0.38
    nością
    0.38
    .$-
    0.38
    最後に
    0.38
    ຟ
    0.38
    土産
    0.38
    畋
    0.37
    组
    0.37
    POSITIVE LOGITS
    *
    0.49
    <h3>
    0.49
    <h2>
    0.40
     parece
    0.39
     tiene
    0.39
     extensible
    0.38
     Kolmogorov
    0.38
     une
    0.38
     benthic
    0.38
     volume
    0.38
    Activations Density 0.005%

    No Known Activations