© 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. 110935
    Prev
    Next
    INDEX
    Explanations

    pushing and pulling

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

    The neuron fires on the imperative, step-by-step instructional language typical of “how-to” directions.

    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
    uição
    -0.92
     được
    -0.90
    angerie
    -0.86
    də
    -0.86
    huawei
    -0.85
     héro
    -0.85
    ocidad
    -0.84
     kysy
    -0.82
    хта
    -0.82
    ectado
    -0.82
    POSITIVE LOGITS
     push
    1.67
     pushing
    1.59
     pull
    1.59
    push
    1.44
     move
    1.38
     pulling
    1.38
     pulled
    1.36
     pushed
    1.36
    Pull
    1.33
     pushes
    1.29
    Activations Density 0.081%

    No Known Activations