© 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. 71936
    Prev
    Next
    INDEX
    Explanations

    company workforce numbers

    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
    𖤍
    -1.39
     the
    -1.34
     of
    -1.23
     websites
    -1.22
     if
    -1.21
     each
    -1.18
     other
    -1.17
    CHREIB
    -1.16
     akzeptieren
    -1.16
    appellant
    -1.13
    POSITIVE LOGITS
     trabajó
    1.48
    Estos
    1.45
     этих
    1.45
     vivió
    1.41
     فقط
    1.39
    はこの
    1.36
    illas
    1.33
    這些
    1.31
     ܙ
    1.30
     employed
    1.30
    Activations Density 0.058%

    No Known Activations