© 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. 57272
    Prev
    Next
    INDEX
    Explanations

    workflow automation

    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
     steps
    0.54
    सि
    0.48
    ին
    0.45
    ਰ
    0.43
    აცი
    0.42
     langkah
    0.42
    ین
    0.41
    xym
    0.41
    榊
    0.41
    蹌
    0.41
    POSITIVE LOGITS
     없는
    0.49
     전에
    0.47
     Lange
    0.46
    limit
    0.45
     কেমন
    0.45
    emotion
    0.45
     جلوگیری
    0.45
    erme
    0.44
    emand
    0.43
    Rights
    0.43
    Activations Density 0.001%

    No Known Activations