© 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. 31-GEMMASCOPE-2-RES-262K
    7. 128430
    Prev
    Next
    INDEX
    Explanations

    physical components or systems

    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
    ᓪ
    0.48
    
    0.46
    竖
    0.46
    AZIONE
    0.45
    ܠܐ
    0.44
    儩
    0.44
     இரண்டு
    0.44
    ้า
    0.44
    凖
    0.44
    ниця
    0.43
    POSITIVE LOGITS
    cells
    0.44
     resonators
    0.41
     turbines
    0.41
     receptors
    0.40
    effects
    0.40
     effects
    0.40
     couplers
    0.40
    oods
    0.39
     (
    0.39
     wineries
    0.39
    Activations Density 0.008%

    No Known Activations