© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8607
    Prev
    Next
    INDEX
    Explanations

    quick word or phrases

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

    The neuron is specialized to detect occurrences of the substring “whip” (e.g. in words like whip, whipsaw, whipstaff).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Olímp
    0.69
     ordre
    0.61
    वला
    0.58
    ឋ
    0.58
     olimp
    0.57
     olla
    0.57
    veille
    0.57
    ពួក
    0.57
     बाजू
    0.57
     olim
    0.56
    POSITIVE LOGITS
    \">\
    0.55
    ...*/
    0.55
    clips
    0.54
    isSelected
    0.54
    
    0.53
    bgColor
    0.52
    '/>
    0.52
    compId
    0.51
     পের
    0.50
     presenceData
    0.48
    Activations Density 0.026%

    No Known Activations