© 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. 99597
    Prev
    Next
    INDEX
    Explanations

    collision occurs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ']->
    -0.80
    beria
    -0.79
    Prerequisite
    -0.77
     חיצוני
    -0.77
     Connection
    -0.77
     deviations
    -0.77
    OSU
    -0.75
     OnEnable
    -0.75
     intermediates
    -0.75
    intermediate
    -0.75
    POSITIVE LOGITS
     collision
    1.55
     OnTriggerEnter
    1.47
     contact
    1.29
     collider
    1.23
     hit
    1.19
     Collision
    1.18
    Collision
    1.13
     collisions
    1.12
    碰
    1.10
     col
    1.09
    Activations Density 0.002%

    No Known Activations