© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 22037
    Prev
    Next
    INDEX
    Explanations

    sensitive data or information

    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
    鐒
    -1.66
    巂
    -1.56
     pescoço
    -1.53
    憮
    -1.51
     aktuell
    -1.47
    derdag
    -1.46
    alakip
    -1.46
     bluz
    -1.45
    ſelves
    -1.44
    lusconi
    -1.42
    POSITIVE LOGITS
    but
    1.95
    even
    1.77
     of
    1.75
     Sensitive
    1.74
     sensitive
    1.73
    where
    1.72
    \
    1.72
    O
    1.63
     if
    1.60
     而
    1.60
    Activations Density 0.034%

    No Known Activations