© 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. 59020
    Prev
    Next
    INDEX
    Explanations

    activatable, activation, activists

    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
     \
    -3.11
     see
    -2.78
    it
    -2.77
     ???
    -2.64
    d
    -2.59
     ใน
    -2.50
     In
    -2.45
    y
    -2.42
     We
    -2.41
    a
    -2.41
    POSITIVE LOGITS
    蕯
    2.86
    㩒
    2.67
    嗞
    2.55
    ers
    2.55
    joueur
    2.50
    s
    2.47
     internacionais
    2.44
    廰
    2.44
    $
    2.42
     gelassen
    2.41
    Activations Density 0.152%

    No Known Activations