© 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. 8538
    Prev
    Next
    INDEX
    Explanations

    component implementations

    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
    .
    -1.95
    全都
    -1.90
     glimpse
    -1.88
    of
    -1.77
    的血
    -1.70
     momentary
    -1.66
     facendo
    -1.65
    </i>
    -1.60
    是由
    -1.60
    的白
    -1.59
    POSITIVE LOGITS
    というわけで
    2.27
     और
    2.20
     și
    2.19
    珦
    2.19
    𖥧
    2.13
    讪
    1.95
    ࿊
    1.95
     १
    1.95
    𝟭
    1.93
    
    1.90
    Activations Density 0.028%

    No Known Activations