© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 60198
    Prev
    Next
    INDEX
    Explanations

    MRI scans

    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
    lgari
    -2.86
     avec
    -2.84
    ーズン
    -2.72
    تیجه
    -2.69
    _))
    -2.67
     With
    -2.55
    )];
    
    -2.55
    s
    -2.52
     Gästen
    -2.52
     sorgfäl
    -2.50
    POSITIVE LOGITS
     realizando
    3.06
    ↵
    2.70
     buscando
    2.52
     comprando
    2.47
     generando
    2.41
    v
    2.39
    o
    2.31
    y
    2.28
     preparando
    2.25
     navegando
    2.13
    Activations Density 0.004%

    No Known Activations