© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44115
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames

    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
    
    -2.88
    ญี่ป
    -2.69
    鳢
    -2.67
    ྂ
    -2.63
    ſelves
    -2.61
     個室
    -2.59
     समीक्षाएं
    -2.55
     weitere
    -2.53
     komplette
    -2.52
    ，“
    -2.50
    POSITIVE LOGITS
    [
    2.94
    It
    2.80
    ),
    2.80
    s
    2.41
    \
    2.38
    ９
    2.38
     `
    2.36
    }$
    2.36
        
    2.33
    They
    2.30
    Activations Density 0.006%

    No Known Activations