© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14692
    Prev
    Next
    INDEX
    Explanations

    end of classification or desired result

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

    The neuron fires strongly on the very first meaningful token of each text chunk, effectively marking the start of a new segment.

    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
     ви
    0.80
     laden
    0.73
     сюжет
    0.71
     groß
    0.68
     Critics
    0.68
    রিষ্ঠ
    0.68
     ходе
    0.67
    դ
    0.67
     хра
    0.66
    থমে
    0.66
    POSITIVE LOGITS
     हेमंत
    0.81
     momen
    0.76
     éventuellement
    0.75
    ESA
    0.74
    knię
    0.74
     마무리
    0.73
    Yard
    0.70
    Village
    0.70
     visant
    0.70
     suitors
    0.70
    Activations Density 0.000%

    No Known Activations