© 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. 84788
    Prev
    Next
    INDEX
    Explanations

    bush and bushes

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

    The neuron responds specifically to the substring “bush.”

    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
    蕺
    -2.83
    鸶
    -2.66
    栊
    -2.45
     verminder
    -2.36
    泐
    -2.33
    鸸
    -2.31
    卺
    -2.20
     薬局
    -2.20
     parachoque
    -2.17
    脔
    -2.17
    POSITIVE LOGITS
     When
    2.97
     Когда
    2.38
    內的
    2.36
     [
    2.23
     большим
    2.20
     the
    2.17
     illogical
    2.13
    *}[
    2.11
     has
    2.06
     assailed
    2.05
    Activations Density 0.004%

    No Known Activations