© 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. 34-GEMMASCOPE-RES-131K
    7. 103285
    Prev
    Next
    INDEX
    Explanations

    journal article citations with years

    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_34/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
     what
    -1.84
     from
    -1.52
     so
    -1.50
     in
    -1.45
     as
    -1.44
    what
    -1.44
     only
    -1.43
     more
    -1.42
     evidently
    -1.41
     also
    -1.41
    POSITIVE LOGITS
    푆
    1.40
     famed
    1.39
     opulent
    1.35
     dekol
    1.35
     Dinas
    1.34
     スリーブ
    1.33
     ornate
    1.32
     اشار
    1.32
     enthou
    1.30
     kabát
    1.30
    Activations Density 0.007%

    No Known Activations