© 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. 100097
    Prev
    Next
    INDEX
    Explanations

    stirring, stirrup

    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
    ’
    -1.91
     were
    -1.63
     had
    -1.47
     Those
    -1.44
     these
    -1.41
     that
    -1.40
     a
    -1.40
     його
    -1.38
     they
    -1.38
     \
    -1.37
    POSITIVE LOGITS
    女
    1.60
     crucial
    1.54
    怎么回事
    1.49
    
    1.48
    ⢕
    1.46
     seulement
    1.46
    攆
    1.45
     hiciera
    1.39
    嫵
    1.38
    
    1.38
    Activations Density 0.008%

    No Known Activations