© 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. 92439
    Prev
    Next
    INDEX
    Explanations

    uint after other tokens

    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
     then
    -1.06
     just
    -1.04
    マツ
    -0.91
     even
    -0.90
     bapt
    -0.88
    acı
    -0.87
    🎍
    -0.85
     alça
    -0.84
     so
    -0.84
    nių
    -0.81
    POSITIVE LOGITS
    heses
    0.97
    yssey
    0.95
    مزید
    0.91
     eventuell
    0.90
    nities
    0.88
    がっ
    0.88
    aneity
    0.88
    imetry
    0.88
    CastException
    0.88
     eventuali
    0.85
    Activations Density 0.026%

    No Known Activations