© 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. 69816
    Prev
    Next
    INDEX
    Explanations

    names and authors

    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
    亹
    -1.48
     misalnya
    -1.39
    MANY
    -1.36
    뻣
    -1.35
    inaison
    -1.34
    isine
    -1.29
     degrés
    -1.28
     seks
    -1.27
    llavero
    -1.27
    Dimensi
    -1.25
    POSITIVE LOGITS
     as
    1.95
     on
    1.54
     their
    1.53
     every
    1.52
     there
    1.48
     some
    1.45
     that
    1.31
     putting
    1.27
     new
    1.26
     each
    1.23
    Activations Density 0.428%

    No Known Activations