© 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. 40-GEMMASCOPE-2-RES-262K
    7. 222918
    Prev
    Next
    INDEX
    Explanations

    linear dimensions

    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_40_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
    scale
    0.41
    smoothed
    0.39
    Flexible
    0.38
    ルー
    0.38
    ध
    0.38
    接
    0.38
    ausea
    0.37
    probability
    0.37
    cleaned
    0.37
    flexible
    0.37
    POSITIVE LOGITS
    STIT
    0.39
    ontiti
    0.37
     tit
    0.37
    chevron
    0.36
     Dự
    0.36
     нового
    0.36
     paras
    0.35
    ORDAN
    0.35
     ಯ
    0.35
     parois
    0.34
    Activations Density 0.001%

    No Known Activations