© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1728
    Prev
    Next
    INDEX
    Explanations

    clearing the way

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

    The neuron strongly activates on words that describe physical movement or displacement (e.g. move, get out, tried, move).

    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
     туры
    -0.75
     wspar
    -0.71
    鴿
    -0.69
    метр
    -0.69
    isio
    -0.67
    atia
    -0.67
    〆
    -0.67
     external
    -0.67
    เที่ยว
    -0.66
    LOC
    -0.66
    POSITIVE LOGITS
     clearing
    1.82
    Clearing
    1.61
     Move
    1.60
     cleared
    1.55
     move
    1.55
     Clearing
    1.52
    Move
    1.48
     aside
    1.47
     vacate
    1.46
    move
    1.44
    Activations Density 0.023%

    No Known Activations