© 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. 14377
    Prev
    Next
    INDEX
    Explanations

    adequate

    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
    "
    -2.52
     beinahe
    -2.47
     mindful
    -2.36
     gänzlich
    -2.31
     sustaining
    -2.30
    鲠
    -2.30
    幷
    -2.27
    嚷
    -2.25
     nahezu
    -2.25
    你可
    -2.25
    POSITIVE LOGITS
    ade
    3.30
    ኧ
    3.17
    ades
    2.73
    ت
    2.50
     praktis
    2.48
     visse
    2.41
    蟥
    2.41
     یک
    2.33
     krim
    2.33
     teater
    2.28
    Activations Density 0.009%

    No Known Activations