© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8949
    Prev
    Next
    INDEX
    Explanations

    compounding interest and capitalization

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

    The neuron fires exclusively at the end-of‐segment marker (“<end>”)—i.e. it detects chunk or section boundaries.

    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_31_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
     글
    0.57
     Outputs
    0.54
     NaN
    0.52
     valeurs
    0.52
     Fehl
    0.51
    一层
    0.50
     استعمال
    0.50
     Dataset
    0.50
    ა
    0.49
    აც
    0.48
    POSITIVE LOGITS
    orio
    0.61
     añadir
    0.59
    specified
    0.58
    orium
    0.57
    TIL
    0.57
    bucket
    0.55
     frecuencia
    0.55
    atlas
    0.53
     भा
    0.53
    ргә
    0.52
    Activations Density 0.002%

    No Known Activations