© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 130881
    Prev
    Next
    INDEX
    Explanations

    W, weight, width, weak, week

    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
     ቫ
    0.41
    堷
    0.39
    鈁
    0.39
     இப்படி
    0.38
     статьи
    0.38
     सध्या
    0.38
    zeugung
    0.38
    クーポン
    0.38
     Víctor
    0.38
     VECTOR
    0.37
    POSITIVE LOGITS
     weights
    0.55
     widths
    0.55
     weight
    0.54
    weight
    0.54
     Weight
    0.52
    weights
    0.52
    w
    0.51
    Weight
    0.50
    重量
    0.50
     width
    0.50
    Activations Density 0.002%

    No Known Activations