© 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. 24-GEMMASCOPE-2-RES-16K
    7. 11925
    Prev
    Next
    INDEX
    Explanations

    UV spectroscopy

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

    The neuron strongly activates on the final substantive word just before a sentence or segment boundary.

    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
    ณฑ
    0.77
    %%%%%%%%%%%%%%%%
    0.74
    >>;
    0.74
    Const
    0.73
    拳
    0.72
    >>>
    0.70
     един
    0.69
    Missense
    0.68
    Overwrite
    0.68
    Transcription
    0.67
    POSITIVE LOGITS
    ien
    0.87
    ievable
    0.79
    iyat
    0.77
     rebounds
    0.75
     baseless
    0.74
    ွမ်း
    0.74
    ুব
    0.73
    iously
    0.73
     Asian
    0.73
    դ
    0.72
    Activations Density 0.000%

    No Known Activations