© 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. 24-GEMMASCOPE-2-RES-16K
    7. 8337
    Prev
    Next
    INDEX
    Explanations

    actions and explanations

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

    The neuron strongly activates on first‐ and second‐person pronouns (“we,” “you,” “your”) used in calls to action or promotional/instructional language.

    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_24_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
    ꯋ
    0.78
     символ
    0.77
     Atkinson
    0.76
    йки
    0.75
     symbolizing
    0.75
    
    0.74
     stockno
    0.74
    Ự
    0.73
    鋈
    0.71
     ANSI
    0.70
    POSITIVE LOGITS
    estado
    0.81
    opens
    0.79
     ранее
    0.79
    take
    0.78
     dov
    0.77
    a
    0.77
    est
    0.76
    feira
    0.76
    tops
    0.75
     anteriormente
    0.75
    Activations Density 0.001%

    No Known Activations