© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66808
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with division and exponentiation

    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
    g
    -1.79
    and
    -1.61
    E
    -1.52
     has
    -1.50
     Now
    -1.48
    などは
    -1.47
    i
    -1.47
     =(
    -1.44
    iální
    -1.43
    a
    -1.41
    POSITIVE LOGITS
    嵓
    1.83
    ᐠ
    1.80
     tesettür
    1.79
    colgante
    1.77
     feroit
    1.76
    ()/
    1.75
     municipios
    1.75
    苼
    1.74
    UKAN
    1.74
     hırka
    1.74
    Activations Density 0.039%

    No Known Activations