© 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. 102789
    Prev
    Next
    INDEX
    Explanations

    affirmation and contrast

    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
     jLabel
    -1.26
    ೣ
    -1.23
     âme
    -1.23
     attaques
    -1.23
     péché
    -1.22
     Soda
    -1.21
     égard
    -1.21
     THAN
    -1.21
    ri
    -1.20
     tiek
    -1.20
    POSITIVE LOGITS
     but
    2.22
    但是
    1.88
    ↵↵
    1.80
     only
    1.61
    selbe
    1.59
     manchmal
    1.52
    但
    1.49
     Verhältnis
    1.43
     But
    1.42
     kteří
    1.39
    Activations Density 0.002%

    No Known Activations