© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 155231
    Prev
    Next
    INDEX
    Explanations

    supply, production, booking, welcome, lead

    np_acts-logits-general · gemini-2.5-flash-lite

    processing sequences sequentially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تصل
    0.44
     antifungal
    0.43
    封
    0.42
    3
    0.41
    دار
    0.40
    얇
    0.40
    بان
    0.39
    -
    0.39
    γα
    0.39
     autod
    0.39
    POSITIVE LOGITS
     PRICES
    0.57
    zaXR
    0.52
    庻
    0.50
     バッグ
    0.50
     பொருளாதார
    0.50
     DNR
    0.50
     HEAD
    0.49
     BOOK
    0.49
    য়ার
    0.48
    aS
    0.48
    Activations Density 0.000%

    No Known Activations