© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 24031
    Prev
    Next
    INDEX
    Explanations

    fractions involving 5

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ܜ
    -2.34
    糴
    -2.25
    งิน
    -2.17
    鱻
    -2.00
     TÉCNICA
    -1.98
    ⤿
    -1.95
     ‘‘
    -1.93
    觊
    -1.88
    zelfde
    -1.86
     estadounid
    -1.85
    POSITIVE LOGITS
     of
    3.72
    1
    2.84
     '
    2.70
    t
    2.50
    '
    2.23
    "
    2.20
    /
    2.13
     (
    2.05
    lo
    2.03
    ap
    1.99
    Activations Density 0.021%

    No Known Activations