© 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. 243
    Prev
    Next
    INDEX
    Explanations

    package structure or code definitions

    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
     Tienen
    -1.72
    outheast
    -1.72
    komplet
    -1.71
     aussit
    -1.70
    figurine
    -1.63
    rolex
    -1.63
    fanart
    -1.60
     ごはん
    -1.59
    aktivi
    -1.58
    halloween
    -1.57
    POSITIVE LOGITS
     is
    2.02
    ll
    1.74
    _
    1.73
     Eigentü
    1.72
    k
    1.62
     Another
    1.55
     p
    1.55
    1
    1.54
    m
    1.53
    l
    1.52
    Activations Density 0.005%

    No Known Activations