© 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. 45300
    Prev
    Next
    INDEX
    Explanations

    categories value listen campaign check

    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
     comentario
    -1.46
     a
    -1.43
    militar
    -1.38
    だいぶ
    -1.37
     slika
    -1.36
     dificultad
    -1.31
     bancada
    -1.30
     burbuja
    -1.30
    ⃢
    -1.29
    鄠
    -1.29
    POSITIVE LOGITS
    这里
    1.44
     each
    1.44
    每个
    1.41
     lyder
    1.39
    each
    1.39
    new
    1.33
    this
    1.33
    here
    1.30
    tie
    1.30
    work
    1.25
    Activations Density 0.030%

    No Known Activations