© 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. 41139
    Prev
    Next
    INDEX
    Explanations

    Sharon followed by a name

    np_acts-logits-general · gemini-2.5-flash-lite

    the proper noun “Sharon.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     makeshift
    -2.52
    ників
    -2.48
    end
    -2.47
     artful
    -2.42
     When
    -2.42
     With
    -2.39
     vanish
    -2.38
     horrific
    -2.36
     sparkly
    -2.36
     excellent
    -2.34
    POSITIVE LOGITS
     the
    3.19
    .
    2.84
     刺繍
    2.78
    
    2.78
    presumably
    2.63
    是他
    2.44
    despite
    2.44
    ية
    2.39
    nearly
    2.38
    而后
    2.30
    Activations Density 0.002%

    No Known Activations