© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69691
    Prev
    Next
    INDEX
    Explanations

    part cases time exceptions degree

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

    This neuron fires on common multiword adverbial qualifiers of extent (e.g. “at least in part,” “to some degree,” “for the first time,” “for the most part”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     about
    -1.66
     produttore
    -1.35
    both
    -1.33
    他有
    -1.33
     proč
    -1.32
    年は
    -1.28
    omans
    -1.26
     including
    -1.23
     because
    -1.21
    ul
    -1.20
    POSITIVE LOGITS
    amkeit
    1.57
    ㎎
    1.51
     niebies
    1.45
    ,
    1.44
    POSSIBLE
    1.41
    糯米
    1.41
    stånd
    1.39
    šče
    1.38
    ки
    1.37
    hör
    1.37
    Activations Density 0.157%

    No Known Activations