© 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. 4010
    Prev
    Next
    INDEX
    Explanations

    Subject:

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

    The neuron fires on forum or email thread metadata tokens—especially numbers (and adjoining words like “Next,” “Previous,” “message,” “Re:”) that mark message IDs or navigation in a thread.

    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
     acrylonitrile
    0.66
     huz
    0.63
     vacuoles
    0.62
    ǥ
    0.62
    मध्ये
    0.60
    leştir
    0.60
     meringue
    0.60
    ěr
    0.60
     chinos
    0.60
    лә
    0.59
    POSITIVE LOGITS
    </a>
    0.78
    rightarrow
    0.73
     Previous
    0.71
    ←
    0.71
    という
    0.69
    →
    0.69
     ←
    0.68
    次は
    0.68
     replied
    0.66
    itemap
    0.65
    Activations Density 0.044%

    No Known Activations