© 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. 127834
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or punctuation

    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
     bluza
    -1.77
     crescere
    -1.69
     विश्वसनीय
    -1.59
    харш
    -1.58
    蛄
    -1.57
     говорил
    -1.57
     tornare
    -1.57
     dealloc
    -1.54
     interessantes
    -1.52
    genen
    -1.52
    POSITIVE LOGITS
     of
    2.00
     if
    1.99
    2
    1.77
    "
    1.66
     для
    1.59
     For
    1.52
    .’”
    1.48
     MASSACHUSETTS
    1.39
    ;
    1.38
     et
    1.38
    Activations Density 0.013%

    No Known Activations