© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119216
    Prev
    Next
    INDEX
    Explanations

    practical application

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

    The neuron activates on the word “hands” as part of “hands-on,” i.e. it detects mentions of practical, hands-on activities or experiences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    地产
    -0.72
    uu
    -0.69
     agave
    -0.68
    udi
    -0.67
     Tere
    -0.66
     Cuth
    -0.65
     Tissue
    -0.65
     overdose
    -0.64
     shave
    -0.63
    ukat
    -0.62
    POSITIVE LOGITS
     ons
    1.73
    ons
    1.64
     Ons
    1.58
    Ons
    1.55
    オン
    1.27
    ONS
    1.20
    ON
    1.18
    On
    1.16
    on
    1.14
     On
    1.14
    Activations Density 0.033%

    No Known Activations