© 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. 6735
    Prev
    Next
    INDEX
    Explanations

    licensed to foundation notices

    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
     first
    -0.88
    doPost
    -0.86
     only
    -0.74
    وء
    -0.74
     when
    -0.73
     procedures
    -0.72
     chem
    -0.70
    logisch
    -0.70
    ஸ்
    -0.70
    explanatory
    -0.69
    POSITIVE LOGITS
    Cette
    0.91
    Article
    0.85
     Internation
    0.84
    ación
    0.84
    ngine
    0.82
    菈
    0.79
    のサ
    0.79
     socialista
    0.79
    vener
    0.78
    chiede
    0.78
    Activations Density 0.003%

    No Known Activations