© 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. 4453
    Prev
    Next
    INDEX
    Explanations

    help me

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

    The neuron fires on words expressing offer of assistance (e.g. “help,” “helping,” 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_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
     discredited
    0.70
     hummus
    0.63
     quiser
    0.62
    Tutorial
    0.61
    レルギー
    0.61
    I
    0.61
     drab
    0.60
    A
    0.60
     pampered
    0.59
     want
    0.58
    POSITIVE LOGITS
     overcome
    0.88
     defray
    0.85
     الحصول
    0.83
     navigate
    0.80
     obtaining
    0.80
     obtain
    0.80
     achieve
    0.78
     mejorar
    0.78
    克服
    0.78
     realizar
    0.77
    Activations Density 0.098%

    No Known Activations