© 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. 13024
    Prev
    Next
    INDEX
    Explanations

    language and technical terms

    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
    ali
    0.47
    alı
    0.47
    및
    0.46
    <unused2130>
    0.46
    และการ
    0.45
    ầm
    0.45
    oi
    0.45
    ối
    0.45
    ถาน
    0.44
    và
    0.44
    POSITIVE LOGITS
     cosidd
    0.61
     B
    0.59
     yang
    0.55
     of
    0.54
     which
    0.54
     L
    0.53
     T
    0.52
     ط
    0.50
     V
    0.50
     která
    0.50
    Activations Density 0.039%

    No Known Activations