© 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. 34-GEMMASCOPE-RES-131K
    7. 45695
    Prev
    Next
    INDEX
    Explanations

    results afforded

    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_34/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
     مانت
    -0.91
     übri
    -0.91
    ötet
    -0.89
    ぐるみ
    -0.89
     السياس
    -0.85
     sulphate
    -0.85
     considerato
    -0.83
     chiamato
    -0.83
     wöch
    -0.82
     Verkäufer
    -0.82
    POSITIVE LOGITS
    vide
    1.25
    Scheme
    1.22
     afford
    1.16
     facile
    1.13
     afforded
    1.11
     affording
    1.05
     affords
    1.02
     Scheme
    0.95
    templ
    0.94
     cleanly
    0.93
    Activations Density 0.409%

    No Known Activations