© 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. 8987
    Prev
    Next
    INDEX
    Explanations

    matcher or header

    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
     to
    -1.63
     would
    -1.59
     my
    -1.41
    ↵↵
    -1.38
     in
    -1.30
     probably
    -1.30
    ↵↵↵
    -1.28
     will
    -1.26
     might
    -1.20
     could
    -1.19
    POSITIVE LOGITS
    Its
    1.61
     ceaseless
    1.42
     Weiterbildung
    1.39
    these
    1.38
    being
    1.38
     Its
    1.38
    鏵
    1.35
     diverses
    1.34
    gså
    1.32
     Lordships
    1.31
    Activations Density 0.016%

    No Known Activations