© 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. 10-GEMMASCOPE-RES-131K
    4. 12083
    Prev
    Next
    INDEX
    Explanations

    often followed by "the" or noun

    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_10/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
     üblichen
    -1.91
     Their
    -1.90
     Both
    -1.81
    {
    -1.75
    鸶
    -1.73
     They
    -1.71
     больших
    -1.70
    隂
    -1.68
     These
    -1.65
     Your
    -1.64
    POSITIVE LOGITS
     the
    2.44
     a
    1.95
     είναι
    1.67
     of
    1.64
    ”
    1.63
    ’
    1.63
    ⃢
    1.61
     boasting
    1.60
    																									
    1.59
     was
    1.56
    Activations Density 0.278%

    No Known Activations