© 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. 90274
    Prev
    Next
    INDEX
    Explanations

    volume, capacity, extent, range

    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
    
    -1.98
    </i>
    -1.97
    眎
    -1.84
    
    -1.73
     navide
    -1.72
     skóry
    -1.70
    ');
    
    -1.69
    衄
    -1.68
     vectorstock
    -1.66
    紜
    -1.64
    POSITIVE LOGITS
     of
    2.39
    </strong>
    2.30
    </em>
    2.25
     is
    1.92
      
    1.87
        
    1.84
    </h4>
    1.75
    <strong>
    1.65
    length
    1.60
     orche
    1.58
    Activations Density 0.009%

    No Known Activations