© 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. 86434
    Prev
    Next
    INDEX
    Explanations

    showing off

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

    The neuron fires strongest on phrases about “showing off,” i.e. expressions that indicate flaunting or showcasing something.

    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
    та
    -2.06
    🕗
    -1.96
    I
    -1.78
    ми
    -1.75
    琑
    -1.73
    『
    -1.73
    )։
    -1.70
     \\
    -1.69
     другими
    -1.68
    S
    -1.64
    POSITIVE LOGITS
    
    1.98
    垪
    1.93
    咵
    1.93
    🫅
    1.91
    ꯳
    1.84
    が増
    1.77
    ᡴ
    1.74
     sice
    1.74
    Opere
    1.72
    泯
    1.72
    Activations Density 0.005%

    No Known Activations