© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128219
    Prev
    Next
    INDEX
    Explanations

    in the case of

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

    This neuron activates on occurrences of the preposition “in” when it introduces a year (e.g. “in 1996”).

    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
     &
    -2.23
     however
    -2.22
     également
    -1.80
     etc
    -1.71
     tetapi
    -1.70
    先是
    -1.65
    >
    -1.58
    彼の
    -1.57
    in
    -1.54
     також
    -1.53
    POSITIVE LOGITS
    螃
    2.02
     Conſ
    1.89
    eſ
    1.73
    actéristi
    1.72
    美国的
    1.71
     anderem
    1.70
     Reſ
    1.69
    ጐ
    1.63
     ส์
    1.63
     dermed
    1.63
    Activations Density 0.091%

    No Known Activations