© 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. 45064
    Prev
    Next
    INDEX
    Explanations

    programming code definitions

    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
     However
    -1.80
     even
    -1.77
     therefore
    -1.68
    what
    -1.62
     what
    -1.62
     truly
    -1.58
     сделать
    -1.55
    This
    -1.55
     mostly
    -1.55
     because
    -1.51
    POSITIVE LOGITS
     animados
    1.54
     armados
    1.52
     vijf
    1.46
     encontraban
    1.46
     SUCH
    1.45
    十分的
    1.45
     mindig
    1.43
    recently
    1.42
     onderdeel
    1.41
    oas
    1.39
    Activations Density 0.005%

    No Known Activations