© 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. 83720
    Prev
    Next
    INDEX
    Explanations

    collision and related physics concepts

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

    This neuron fires on highly technical, domain‐specific scientific text—especially detailed descriptions of granular gas hydrodynamics and transport coefficients.

    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
    rifft
    -0.77
    ladin
    -0.69
    RICS
    -0.68
     disposizione
    -0.65
     übrig
    -0.65
    ografija
    -0.65
    expenses
    -0.64
    IW
    -0.63
    魔法
    -0.63
    uhkan
    -0.63
    POSITIVE LOGITS
     collision
    1.27
    collision
    1.15
     Collision
    1.13
     Knudsen
    1.13
     Grad
    1.05
     collide
    1.05
    Collision
    1.00
    碰撞
    0.97
     collided
    0.97
    Grad
    0.96
    Activations Density 0.017%

    No Known Activations