© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15852
    Prev
    Next
    INDEX
    Explanations

    deliveries and completion

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

    The neuron fires on commercial pitches or service‐offer language—sentences where someone promotes what they can create or do (e.g. “I can create a quality design for your T-shirts,” “please solve this problem,” etc.).

    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
     (!)
    0.68
    (!)
    0.62
     seseorang
    0.59
    <b>
    0.58
    
    0.56
    ѕ
    0.54
    <0xEF>
    0.54
    ’!
    0.52
     (!
    0.50
    (!
    0.50
    POSITIVE LOGITS
     Accuracy
    0.66
     xls
    0.66
    無料で
    0.64
     accuracy
    0.64
    accuracy
    0.63
     качественно
    0.63
     github
    0.63
     utf
    0.61
     según
    0.61
    成績
    0.61
    Activations Density 0.046%

    No Known Activations