© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127902
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs and common collocations

    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
    ...
    -1.55
    .
    -1.40
     ...
    -1.38
    '
    -1.33
    وق
    -1.33
    够了
    -1.25
     «
    -1.20
     Interesse
    -1.16
     chante
    -1.15
     so
    -1.14
    POSITIVE LOGITS
    ösungen
    1.59
    (
    1.56
     několika
    1.55
     also
    1.52
     and
    1.46
    Our
    1.41
     içeris
    1.40
     with
    1.38
     שלנו
    1.37
    cún
    1.36
    Activations Density 0.074%

    No Known Activations