© 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. 86586
    Prev
    Next
    INDEX
    Explanations

    review ratings and questions

    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
     it
    -2.22
     this
    -2.06
     as
    -1.79
     which
    -1.65
     with
    -1.59
     where
    -1.56
     two
    -1.53
     واض
    -1.51
     these
    -1.50
     through
    -1.45
    POSITIVE LOGITS
    ︲
    1.80
     nové
    1.73
    ੳ
    1.69
     utiliser
    1.61
    afterEach
    1.61
     use
    1.59
     OFDb
    1.53
    JAMES
    1.53
    Ál
    1.51
     nieuwe
    1.50
    Activations Density 0.066%

    No Known Activations