© 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. 85645
    Prev
    Next
    INDEX
    Explanations

    `//` or "Q:" or "Dolph" or "Imaging"

    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
     unrelenting
    -2.75
     unwavering
    -2.66
     unruly
    -2.59
     burgeoning
    -2.58
     lavish
    -2.55
     blatantly
    -2.55
     exuberant
    -2.55
     revital
    -2.50
     frantic
    -2.47
     If
    -2.44
    POSITIVE LOGITS
    '
    3.44
    .
    3.30
    ness
    3.03
     giu
    2.77
     frequentemente
    2.73
    er
    2.70
     praticamente
    2.67
    和他
    2.55
    ity
    2.50
     Dinas
    2.48
    Activations Density 0.000%

    No Known Activations