© 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. 189269
    Prev
    Next
    INDEX
    Explanations

    Units, Wage

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

    units, numbers, or specific contexts

    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
     желез
    0.48
    သည့်
    0.46
     मारने
    0.45
    冰箱
    0.44
    issaient
    0.43
    孜
    0.43
    ését
    0.43
    不敢
    0.43
    quered
    0.43
    બાદ
    0.43
    POSITIVE LOGITS
    r
    0.54
     Units
    0.52
     গঠ
    0.50
     units
    0.47
    ме
    0.47
    Units
    0.47
     Wage
    0.46
    िंक
    0.46
    nä
    0.45
     unità
    0.45
    Activations Density 0.001%

    No Known Activations