© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103521
    Prev
    Next
    INDEX
    Explanations

    ba

    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
    a
    -3.25
    ly
    -3.06
    鲧
    -2.92
    an
    -2.73
    i
    -2.72
     GOtt
    -2.69
    い
    -2.66
     jezt
    -2.58
    ed
    -2.55
    اً
    -2.52
    POSITIVE LOGITS
    rinology
    2.66
    棪
    2.64
     "
    2.58
    本当に
    2.50
    <
    2.48
    行く
    2.42
     
    2.39
     forego
    2.36
    仿佛
    2.27
    vantaged
    2.23
    Activations Density 0.006%

    No Known Activations