© 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. 44984
    Prev
    Next
    INDEX
    Explanations

    fax machines

    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
     兒童
    -3.20
    żli
    -2.77
     ซึ่ง
    -2.73
    vidades
    -2.69
    仃
    -2.67
     conferencias
    -2.66
    爻
    -2.61
    驒
    -2.61
    lickr
    -2.58
     glaubt
    -2.53
    POSITIVE LOGITS
    e
    4.66
    to
    3.80
    a
    3.52
    ar
    3.33
     '
    3.11
    1
    2.92
    q
    2.86
    the
    2.84
    ↵↵
    2.72
    ing
    2.72
    Activations Density 0.001%

    No Known Activations