© 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. 22-GEMMASCOPE-RES-131K
    7. 68994
    Prev
    Next
    INDEX
    Explanations

    smooth changes and animation

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

    The neuron flags terms that denote dynamic changes or transitions—e.g. animation/animate, CSS transitions, rate‐of‐change, scanning rate, and similar words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     ulteriori
    -1.00
     pericolo
    -0.99
     rood
    -0.99
     munc
    -0.98
     oop
    -0.96
    OIS
    -0.96
     ripet
    -0.94
     incontri
    -0.92
     étrangers
    -0.92
    シンプル
    -0.92
    POSITIVE LOGITS
     transitions
    1.44
     transitioning
    1.37
     transition
    1.36
     between
    1.20
     transitional
    1.19
     переход
    1.19
     Transition
    1.17
    ransition
    1.14
     slowest
    1.13
     slower
    1.12
    Activations Density 0.076%

    No Known Activations