© 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. 42905
    Prev
    Next
    INDEX
    Explanations

    about with numerical quantities

    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
     camiones
    -1.78
     dinosaurios
    -1.76
     définir
    -1.68
    擽
    -1.66
     our
    -1.63
    riched
    -1.59
     aceptación
    -1.59
     your
    -1.59
    モア
    -1.59
     colocación
    -1.58
    POSITIVE LOGITS
     in
    2.00
     
    1.88
    P
    1.67
    '
    1.66
     “
    1.60
     \
    1.54
     If
    1.51
     (
    1.42
    "
    1.41
     Because
    1.40
    Activations Density 0.048%

    No Known Activations