© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8564
    Prev
    Next
    INDEX
    Explanations

    references and directives

    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
     when
    -2.17
     their
    -1.98
     showing
    -1.93
     incorporating
    -1.77
     specially
    -1.76
     meticulously
    -1.74
     allowing
    -1.70
     mainly
    -1.70
     focusing
    -1.70
     encompassing
    -1.66
    POSITIVE LOGITS
     of
    2.36
    6
    1.95
    3
    1.93
    7
    1.91
     REALLY
    1.89
    THERE
    1.80
     VERY
    1.79
    4
    1.73
     FIRST
    1.64
    TWO
    1.64
    Activations Density 0.034%

    No Known Activations