© 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. 87200
    Prev
    Next
    INDEX
    Explanations

    New York University

    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
    〽
    -0.85
     balance
    -0.77
     Booklet
    -0.75
    cese
    -0.73
    jillo
    -0.69
     kuto
    -0.68
     Brentford
    -0.68
    ἦ
    -0.68
    エラ
    -0.67
     uwagę
    -0.67
    POSITIVE LOGITS
     UAE
    0.91
    UAE
    0.85
     takı
    0.82
     NYU
    0.76
    ichord
    0.75
     Schell
    0.75
    LAY
    0.75
     Abu
    0.75
    ıc
    0.74
    server
    0.73
    Activations Density 0.013%

    No Known Activations