© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40056
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure

    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
     "
    -1.78
     rosado
    -1.62
     then
    -1.57
     but
    -1.55
    
    -1.48
    </h2>
    -1.47
     δὲ
    -1.45
    '
    -1.44
     an
    -1.42
    ("
    -1.42
    POSITIVE LOGITS
    ↵↵
    1.84
    malıdır
    1.80
     and
    1.72
    maktadır
    1.70
    剮
    1.63
    contacto
    1.51
     slugs
    1.45
     ymm
    1.40
     })
    
    1.38
     chun
    1.38
    Activations Density 0.042%

    No Known Activations