© 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. 110764
    Prev
    Next
    INDEX
    Explanations

    check

    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
     even
    -1.01
     before
    -0.96
     although
    -0.92
     because
    -0.91
     whether
    -0.89
     by
    -0.88
     does
    -0.88
     actually
    -0.84
    As
    -0.79
     began
    -0.79
    POSITIVE LOGITS
    CHECK
    1.03
     fatal
    1.01
    check
    0.97
    チェック
    0.97
    checked
    0.96
     CHECK
    0.95
     check
    0.93
     Check
    0.91
    died
    0.91
    Check
    0.88
    Activations Density 0.006%

    No Known Activations