© 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. 74839
    Prev
    Next
    INDEX
    Explanations

    school grade levels

    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
     is
    -1.74
    x
    -1.70
    -
    -1.59
     its
    -1.56
    8
    -1.50
     of
    -1.48
    !
    -1.47
     has
    -1.46
    <
    -1.46
     they
    -1.38
    POSITIVE LOGITS
     deudas
    1.70
    趼
    1.45
    izoen
    1.45
    ẑ
    1.45
     huellas
    1.43
    ーす
    1.41
    ALLENGE
    1.40
    cuentos
    1.39
    izamos
    1.38
     emisiones
    1.38
    Activations Density 0.014%

    No Known Activations