© 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. 99376
    Prev
    Next
    INDEX
    Explanations

    psychomotor and manual dexterity

    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
     there
    -2.03
     it
    -1.71
     on
    -1.66
    R
    -1.55
     has
    -1.51
     they
    -1.49
    X
    -1.48
     more
    -1.43
     before
    -1.41
    V
    -1.41
    POSITIVE LOGITS
     intrigu
    1.62
     "")
    1.57
    ⻬
    1.56
     modernes
    1.49
    𐬹
    1.48
    
    1.48
    偸
    1.48
    בוד
    1.48
     gallant
    1.46
    Hilsen
    1.46
    Activations Density 0.042%

    No Known Activations