© 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. 58633
    Prev
    Next
    INDEX
    Explanations

    ADVERTISEMENT

    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
    generally
    -1.62
    鹩
    -1.60
     chó
    -1.60
     associés
    -1.59
    might
    -1.52
     zwi
    -1.52
    particularly
    -1.49
    probably
    -1.48
     bụ
    -1.47
    ఽ
    -1.47
    POSITIVE LOGITS
     with
    2.41
     when
    2.33
     not
    2.05
     while
    1.99
     how
    1.95
     from
    1.86
     which
    1.82
     before
    1.80
     what
    1.75
     in
    1.72
    Activations Density 0.003%

    No Known Activations