© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99318
    Prev
    Next
    INDEX
    Explanations

    annual awards and events

    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
     promocional
    -1.84
     utilizados
    -1.82
     две
    -1.79
    してます
    -1.73
    鸾
    -1.63
     distribuidor
    -1.60
     utilizamos
    -1.59
     usamos
    -1.59
     semanal
    -1.59
     haremos
    -1.57
    POSITIVE LOGITS
    r
    2.42
    c
    2.33
    m
    2.27
    b
    2.09
    f
    1.98
    .”
    1.97
    l
    1.96
     of
    1.85
    k
    1.82
    s
    1.77
    Activations Density 0.011%

    No Known Activations