© 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. 67165
    Prev
    Next
    INDEX
    Explanations

    directly applied or extended

    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
    _
    -1.65
    鸸
    -1.45
     finales
    -1.38
     injust
    -1.37
     REALLY
    -1.36
     ân
    -1.36
    푉
    -1.35
     conduc
    -1.34
     repeti
    -1.34
    嵛
    -1.33
    POSITIVE LOGITS
     without
    2.00
     because
    1.98
     from
    1.90
    しましたが
    1.59
     with
    1.58
     although
    1.55
     パウダー
    1.55
    骞
    1.52
     countless
    1.52
     antworten
    1.50
    Activations Density 0.061%

    No Known Activations