© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70923
    Prev
    Next
    INDEX
    Explanations

    create new project file

    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
    ll
    -1.42
     enorme
    -1.31
     murale
    -1.29
     inge
    -1.28
    rs
    -1.27
    ls
    -1.26
    figure
    -1.24
     proble
    -1.23
     ROBERT
    -1.20
    maybe
    -1.20
    POSITIVE LOGITS
     about
    1.89
     for
    1.61
     in
    1.59
     that
    1.41
     before
    1.31
     such
    1.27
     there
    1.26
     создать
    1.22
     so
    1.19
    肖
    1.18
    Activations Density 0.083%

    No Known Activations