© 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. 100014
    Prev
    Next
    INDEX
    Explanations

    per year

    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
     hará
    -1.88
    痦
    -1.80
     are
    -1.69
     beberapa
    -1.67
    那你
    -1.59
     antics
    -1.55
     várias
    -1.55
     vários
    -1.52
     defied
    -1.45
    所以我
    -1.44
    POSITIVE LOGITS
    At
    1.80
    Even
    1.71
    A
    1.62
    We
    1.62
    T
    1.60
    R
    1.60
     custodia
    1.57
    D
    1.53
    V
    1.52
    们
    1.50
    Activations Density 0.026%

    No Known Activations