© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 11814
    Prev
    Next
    INDEX
    Explanations

    image file names and captions

    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
    ℅
    -0.81
    #
    -0.77
     局
    -0.75
    phinx
    -0.72
    局
    -0.71
    әрмәләр
    -0.71
    никах
    -0.71
     wreath
    -0.71
     Ames
    -0.70
     Oswald
    -0.69
    POSITIVE LOGITS
     nomination
    0.91
     nom
    0.91
     nominated
    0.85
     Nominations
    0.85
     nominations
    0.85
    itzt
    0.84
     FAC
    0.84
     candidate
    0.82
     Cleanup
    0.81
    Nomin
    0.80
    Activations Density 0.045%

    No Known Activations