© 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. 40183
    Prev
    Next
    INDEX
    Explanations

    apostrophe followed by 's'

    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
     unwavering
    -2.17
     by
    -2.13
     their
    -2.11
     if
    -2.09
     noteworthy
    -2.06
     when
    -1.91
     When
    -1.91
     expertly
    -1.88
     meticulously
    -1.81
     unrelenting
    -1.81
    POSITIVE LOGITS
    鬭
    2.16
    侔
    2.09
     iſt
    2.06
    ڧ
    1.98
    
    1.91
     😁
    1.91
     !!!!!
    1.86
     !!!!
    1.86
     hecta
    1.84
     😄
    1.77
    Activations Density 0.009%

    No Known Activations