© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37301
    Prev
    Next
    INDEX
    Explanations

    items that go into boxes or tanks

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

    technical terms and company types

    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
     blush
    0.46
    ↵
    0.46
     D
    0.44
    าม
    0.42
     DWI
    0.42
     stesso
    0.42
     Özel
    0.42
     bulk
    0.41
    霏
    0.41
    ్వర
    0.41
    POSITIVE LOGITS
    browser
    0.52
    science
    0.50
    linux
    0.50
    📏
    0.50
    glyphicon
    0.49
    iziModal
    0.49
    pictureBox
    0.49
    sport
    0.49
    玩意
    0.49
    iophorus
    0.48
    Activations Density 0.000%

    No Known Activations