© 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. 17499
    Prev
    Next
    INDEX
    Explanations

    letter here or on

    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
    <start_of_image>
    0.54
    et
    0.54
     be
    0.49
    リ
    0.47
     suur
    0.47
    sprechend
    0.47
    p
    0.47
     näytt
    0.46
    ح
    0.46
    comment
    0.45
    POSITIVE LOGITS
    ప్ప
    0.47
    avacak
    0.45
     시설
    0.45
     Severity
    0.45
     hemolytic
    0.45
    📤
    0.44
     స్థ
    0.43
    лян
    0.42
     கப்
    0.42
    ων
    0.42
    Activations Density 0.001%

    No Known Activations