© 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. 101504
    Prev
    Next
    INDEX
    Explanations

    photo, photos, photograph

    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
     they
    -2.22
    of
    -1.98
    京东
    -1.75
    偏偏
    -1.63
    ist
    -1.63
     solamente
    -1.62
    目の
    -1.61
     willingness
    -1.61
     baskılı
    -1.59
    ̙
    -1.59
    POSITIVE LOGITS
     gekenn
    2.11
     zugel
    1.99
     Geset
    1.95
    יה
    1.91
    婞
    1.89
     produite
    1.89
     Stornier
    1.89
    夲
    1.88
     deniz
    1.88
     Presumably
    1.88
    Activations Density 0.018%

    No Known Activations