© 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. 129455
    Prev
    Next
    INDEX
    Explanations

    function approximation

    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
     of
    -1.50
     in
    -1.45
    君は
    -1.22
    々に
    -1.16
     acadé
    -1.15
     was
    -1.13
    ará
    -1.13
    вла
    -1.09
     možnost
    -1.08
     will
    -1.06
    POSITIVE LOGITS
     who
    1.78
     musst
    1.59
    atecas
    1.38
     immagine
    1.33
    在一个
    1.30
    我們
    1.28
     bronzo
    1.28
    Debe
    1.27
     quelconque
    1.26
     borgo
    1.25
    Activations Density 0.066%

    No Known Activations