© 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. 83249
    Prev
    Next
    INDEX
    Explanations

    collision and impact

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

    The neuron fires strongly on words describing physical impacts or hits (e.g. “hit,” “hitting,” “hits”).

    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
    淫
    -0.85
    Важно
    -0.79
    ולוג
    -0.75
    膣
    -0.74
    ๋
    -0.74
     confeder
    -0.73
    谴
    -0.73
    UNCIL
    -0.73
    wnie
    -0.72
     ux
    -0.71
    POSITIVE LOGITS
     contact
    1.28
     collision
    1.28
     collisions
    1.09
     hits
    1.09
     helmet
    1.05
    Collision
    1.02
    collision
    0.99
     Collision
    0.94
     deliver
    0.93
     kontakt
    0.92
    Activations Density 0.012%

    No Known Activations