© 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. 33005
    Prev
    Next
    INDEX
    Explanations

    legal, location, teams

    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
     All
    -1.02
    All
    -1.00
    all
    -0.91
    ALL
    -0.84
     Herrschaft
    -0.75
    vě
    -0.72
     courtship
    -0.71
     filtration
    -0.71
    allo
    -0.69
     dois
    -0.69
    POSITIVE LOGITS
     shillings
    0.73
     sixteen
    0.70
    putExtra
    0.68
     leçon
    0.67
    iama
    0.67
     serdecznie
    0.66
    オン
    0.64
     seater
    0.63
     levelling
    0.63
     lind
    0.62
    Activations Density 0.213%

    No Known Activations