© 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. 21522
    Prev
    Next
    INDEX
    Explanations

    numbers or list items

    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
    movimiento
    -1.31
     durchaus
    -1.29
    Yorkshire
    -1.26
    Obstacles
    -1.25
    Referees
    -1.25
    )
    -1.24
    鼷
    -1.23
     hermosas
    -1.23
     bundles
    -1.22
    Queensland
    -1.22
    POSITIVE LOGITS
     produisons
    1.54
     truk
    1.52
     détach
    1.45
    дарт
    1.42
    vane
    1.41
    сом
    1.39
    偸
    1.39
     while
    1.38
     informée
    1.38
     golfe
    1.38
    Activations Density 0.029%

    No Known Activations