© 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. 111990
    Prev
    Next
    INDEX
    Explanations

    contrast with typical actions

    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
    in
    0.54
    ojen
    0.51
    enarios
    0.46
    ipal
    0.46
    ler
    0.46
    news
    0.45
    ests
    0.45
    _
    0.45
    items
    0.45
    patterns
    0.44
    POSITIVE LOGITS
     decreed
    0.50
    ઢ
    0.47
     confessed
    0.46
    確か
    0.45
     owned
    0.43
    дили
    0.42
     まで
    0.41
     первого
    0.41
    یدم
    0.41
     supposedly
    0.41
    Activations Density 0.001%

    No Known Activations