© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74776
    Prev
    Next
    INDEX
    Explanations

    conjugal, Congregational, crotch, reticulocytes

    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
    
    -3.56
    鱘
    -3.56
    
    -3.53
    郿
    -3.48
    阗
    -3.20
     kapture
    -3.19
    諼
    -3.16
    
    -3.14
    llavero
    -3.11
    蔸
    -3.08
    POSITIVE LOGITS
    .
    3.95
     
    3.94
    us
    3.59
    –
    3.31
    ’
    3.09
    er
    3.05
    de
    3.00
    ↵
    2.91
     "
    2.81
    G
    2.81
    Activations Density 0.013%

    No Known Activations