© 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. 69
    Prev
    Next
    INDEX
    Explanations

    but (contrast)

    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
    it
    -1.52
    its
    -1.48
    as
    -1.48
    t
    -1.48
    m
    -1.45
     Eight
    -1.36
    k
    -1.34
     its
    -1.32
     Smaller
    -1.31
     pulsante
    -1.30
    POSITIVE LOGITS
    哐
    1.45
     圈
    1.35
    この日
    1.34
    vollen
    1.32
    ㈱
    1.31
     adecu
    1.31
    棪
    1.30
     女孩
    1.29
    啵
    1.27
     korban
    1.23
    Activations Density 0.061%

    No Known Activations