© 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. 186149
    Prev
    Next
    INDEX
    Explanations

    quantities expressed as percentages or fractions

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

    percentages of amounts

    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
     fingerprints
    0.40
    夂
    0.40
    இவ்வாறு
    0.39
     dvije
    0.39
     zwei
    0.39
     indexOf
    0.39
     две
    0.38
    джи
    0.38
     benefiting
    0.38
     dvě
    0.38
    POSITIVE LOGITS
     total
    0.52
    total
    0.51
     tota
    0.49
     totales
    0.48
     মোট
    0.47
    总量
    0.47
    総
    0.46
    总体
    0.45
     Gesamt
    0.45
     totale
    0.44
    Activations Density 0.069%

    No Known Activations