© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 98680
    Prev
    Next
    INDEX
    Explanations

    locations and times

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

    This neuron detects prepositions (especially “at” and “in”) that introduce time or location details.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     THESE
    -1.71
     («
    -1.70
    놋
    -1.60
     dragón
    -1.60
    筴
    -1.59
     existant
    -1.58
     gastronomía
    -1.56
     DURING
    -1.56
     пользователя
    -1.53
     ({
    -1.52
    POSITIVE LOGITS
     but
    2.23
     of
    2.13
     before
    2.08
     from
    1.93
     with
    1.91
     as
    1.82
     at
    1.80
     only
    1.75
     by
    1.65
     including
    1.63
    Activations Density 0.005%

    No Known Activations