© 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. 8969
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on the final subword pieces that complete a multi‐token word (i.e. word-ending subword 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_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
    ;
    0.82
    ?
    0.78
    :
    0.77
     plague
    0.74
     등에
    0.69
     سامنا
    0.69
    很难
    0.67
     სახელმწიფო
    0.67
    和社会
    0.65
     втра
    0.64
    POSITIVE LOGITS
     Benutzer
    0.86
     Bany
    0.83
    購物
    0.82
     Bildschirm
    0.80
     Boden
    0.80
     persevere
    0.79
     Stück
    0.79
    ك
    0.79
     labores
    0.78
     rote
    0.77
    Activations Density 0.000%

    No Known Activations