© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 32980
    Prev
    Next
    INDEX
    Explanations

    cruising speed and highway driving

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

    The main thing this neuron does is detect numeric measurements and values (especially units like torque, speed, acceleration, distances).

    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
    دي
    -1.01
    enskap
    -0.86
    島
    -0.85
    sieke
    -0.84
    PutPixel
    -0.83
    Ẻ
    -0.83
    niaus
    -0.82
    ateurs
    -0.82
     ультра
    -0.82
    теров
    -0.81
    POSITIVE LOGITS
     cruise
    1.70
     Cruise
    1.45
    Cruise
    1.43
     cruising
    1.40
    cruise
    1.38
     highway
    1.24
     cruises
    1.09
     at
    1.05
     Highway
    0.93
    cru
    0.93
    Activations Density 0.011%

    No Known Activations