© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1779
    Prev
    Next
    INDEX
    Explanations

    complex manifolds, plane, domain

    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
    "',
    -1.23
     euer
    -1.16
    målet
    -1.13
    '';
    -1.13
    側は
    -1.11
    ÃO
    -1.11
    '].
    -1.09
    x
    -1.09
     baterai
    -1.09
     scolas
    -1.08
    POSITIVE LOGITS
    おわりに
    1.34
    Martín
    1.14
    binden
    1.13
    traceback
    1.10
     Trotz
    1.09
    ตร์
    1.08
    缈
    1.07
    ínguez
    1.05
    ítimo
    1.04
    ualitas
    1.02
    Activations Density 0.013%

    No Known Activations