© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7196
    Prev
    Next
    INDEX
    Explanations

    presence or indication

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

    The neuron fires on tokens that appear in formal announcement or document‐section headings (e.g. “announces,” “announced,” “Statement of …,” “reports,” 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
     /(\
    0.60
    plicial
    0.59
     กราบ
    0.57
    ampang
    0.57
    rupole
    0.57
     приведен
    0.57
     بتوان
    0.56
    =-\
    0.56
    heiro
    0.54
     पटेल
    0.54
    POSITIVE LOGITS
     existence
    1.20
    existence
    1.20
     existência
    1.20
     intentions
    1.16
     presença
    1.15
     existencia
    1.13
     наличие
    1.13
     intention
    1.11
     adanya
    1.09
    的存在
    1.08
    Activations Density 0.394%

    No Known Activations