© 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. 69826
    Prev
    Next
    INDEX
    Explanations

    diversity and variety

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

    The neuron primarily detects words and phrases that express diversity or variety (e.g., “diversity,” “diverse,” “variety”).

    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
     Probably
    -2.28
     ewigen
    -2.19
     vorigen
    -2.19
     Since
    -2.14
     höchsten
    -2.14
     This
    -2.13
     jeweiligen
    -2.09
     Perhaps
    -2.06
     Almost
    -2.05
     Honestly
    -2.03
    POSITIVE LOGITS
    簪
    1.91
     anadolu
    1.84
    地看着
    1.77
    ︲
    1.70
    ⼥
    1.66
    and
    1.66
     lour
    1.64
    
    1.63
    蒾
    1.62
    thodoxy
    1.61
    Activations Density 0.011%

    No Known Activations