© 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. 77189
    Prev
    Next
    INDEX
    Explanations

    list items and separators

    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
     or
    0.55
    0
    0.46
     모델
    0.45
     목
    0.45
    худ
    0.45
    uckle
    0.44
     exacerbated
    0.43
     unavoidable
    0.43
    hnen
    0.43
     결정
    0.42
    POSITIVE LOGITS
     پیسې
    0.47
     bg
    0.45
    后
    0.45
    ौला
    0.44
     xương
    0.43
     nonEmpty
    0.43
     الغ
    0.43
     freq
    0.43
    Hib
    0.43
    ές
    0.42
    Activations Density 0.000%

    No Known Activations