© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12885
    Prev
    Next
    INDEX
    Explanations

    With followed by question words or descriptive adjectives

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

    The neuron strongly fires on the first few words of a new sentence or segment (i.e. sentence-initial tokens).

    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
    whereas
    0.61
     후에
    0.59
    实际上
    0.57
    which
    0.57
    は見
    0.57
     whereas
    0.56
    告诉
    0.56
    亦
    0.56
     resulted
    0.56
    Asimismo
    0.56
    POSITIVE LOGITS
    这么多
    0.88
     hindsight
    0.85
    越来越多的
    0.83
     tantas
    0.80
    越來越
    0.78
    這麼
    0.77
     advent
    0.77
     इतनी
    0.77
     tantos
    0.77
     recentes
    0.75
    Activations Density 0.165%

    No Known Activations