© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13286
    Prev
    Next
    INDEX
    Explanations

    question words and phrases

    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
     precioso
    -1.60
     desmotiv
    -1.45
     extranjera
    -1.41
    龉
    -1.37
     condicionado
    -1.32
    珰
    -1.31
     asiática
    -1.30
     autres
    -1.30
    chevêque
    -1.30
    codiles
    -1.27
    POSITIVE LOGITS
     of
    1.93
     they
    1.52
    Without
    1.50
     these
    1.49
    When
    1.45
     noticeably
    1.43
     to
    1.34
     is
    1.31
     which
    1.30
    Very
    1.30
    Activations Density 0.029%

    No Known Activations