© 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. 13339
    Prev
    Next
    INDEX
    Explanations

    state change and outcomes

    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
    を使って
    -1.63
     about
    -1.50
    annique
    -1.32
    可以
    -1.32
    已经
    -1.29
     beda
    -1.29
    を使った
    -1.27
     Inſ
    -1.26
     víc
    -1.26
     två
    -1.25
    POSITIVE LOGITS
     in
    1.67
     and
    1.44
     if
    1.42
     would
    1.40
     are
    1.40
     of
    1.39
     there
    1.30
     republiky
    1.30
     it
    1.29
     such
    1.25
    Activations Density 0.787%

    No Known Activations