© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104539
    Prev
    Next
    INDEX
    Explanations

    titles enclosed in quotes

    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_22/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
     sillas
    -1.44
     verkoop
    -1.41
    際には
    -1.37
     activiteiten
    -1.34
    zaamheid
    -1.27
     onderdelen
    -1.27
     guerras
    -1.27
     kaart
    -1.22
     tevreden
    -1.22
    たびに
    -1.20
    POSITIVE LOGITS
    があり
    1.38
     the
    1.38
     a
    1.38
    LOYEES
    1.31
    ,
    1.27
     (
    1.27
    調味料
    1.23
     of
    1.23
    the
    1.23
    <strong>
    1.21
    Activations Density 0.033%

    No Known Activations