© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1730
    Prev
    Next
    INDEX
    Explanations

    phrases following "it's"

    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
     using
    -1.78
     dozens
    -1.60
     those
    -1.59
     allows
    -1.57
     people
    -1.54
    Because
    -1.54
     used
    -1.52
     our
    -1.52
     on
    -1.49
     moglie
    -1.48
    POSITIVE LOGITS
    螃
    1.73
    
    1.59
    鲥
    1.58
    蠓
    1.53
     rése
    1.52
     bolsillos
    1.52
    vertre
    1.50
     Reſ
    1.46
    €”
    1.46
    berat
    1.45
    Activations Density 0.028%

    No Known Activations