© 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. 67423
    Prev
    Next
    INDEX
    Explanations

    linking words with and

    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
     разнообраз
    -1.74
     Begleitung
    -1.60
     Rücksicht
    -1.56
     wią
    -1.49
    Both
    -1.48
     Kenntnis
    -1.41
     freundlichen
    -1.39
     постоянно
    -1.38
    According
    -1.38
     various
    -1.38
    POSITIVE LOGITS
     ...
    1.53
     else
    1.39
     digno
    1.30
     unſ
    1.25
    aconda
    1.24
     conducta
    1.22
     colección
    1.18
     proudly
    1.18
     oscuridad
    1.18
     domingo
    1.17
    Activations Density 0.054%

    No Known Activations