© 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. 103921
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "well" or "wells"

    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
     well
    -1.20
    也非常
    -0.82
     тебя
    -0.79
    ቴ
    -0.76
     darbu
    -0.76
    Picking
    -0.75
     dividida
    -0.74
     Erwä
    -0.71
    楽しめます
    -0.70
    楽しめる
    -0.69
    POSITIVE LOGITS
    ogram
    0.95
    being
    0.89
    spring
    0.88
    entiation
    0.88
     febrero
    0.85
    pell
    0.85
     Wai
    0.84
    itization
    0.83
    thole
    0.82
    cations
    0.82
    Activations Density 0.023%

    No Known Activations