© 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. 5967
    Prev
    Next
    INDEX
    Explanations

    the word 'here'

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

    This neuron strongly activates on the final substantive word at the end of each segment (i.e. the last content word immediately before an `<end>`).

    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
    ’
    0.69
     ซ
    0.67
     basses
    0.65
     =
    0.61
     Smoking
    0.61
     Τα
    0.61
     경우는
    0.61
    TING
    0.61
     οπο
    0.61
    اطع
    0.61
    POSITIVE LOGITS
    jší
    0.76
    𐰇
    0.74
    jiang
    0.71
    แห่ง
    0.71
     이곳
    0.70
    这里的
    0.67
     правительства
    0.67
    䅐
    0.66
     இங்கு
    0.64
    mvc
    0.64
    Activations Density 0.001%

    No Known Activations