© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98983
    Prev
    Next
    INDEX
    Explanations

    opening quotes followed by speech

    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
    ing
    -1.73
    Forgery
    -1.40
    </h4>
    -1.39
     them
    -1.35
     даже
    -1.33
     altres
    -1.33
    𝘔
    -1.33
     Según
    -1.30
    Barriers
    -1.30
     isnt
    -1.29
    POSITIVE LOGITS
    
    1.41
    govine
    1.40
    ܜ
    1.39
     cuándo
    1.38
    鲧
    1.36
    enzen
    1.35
     to
    1.34
    هران
    1.32
     tevreden
    1.30
    銠
    1.30
    Activations Density 0.024%

    No Known Activations