© 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. 22-GEMMASCOPE-RES-131K
    4. 519
    Prev
    Next
    INDEX
    Explanations

    css animation and transitions

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

    This neuron detects mentions of animation timing/easing functions (e.g. “ease,” “easing,” “interpolator,” “transition” terms).

    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
    縂
    -1.18
     need
    -1.15
     abbra
    -1.11
     pronti
    -1.10
     ricordare
    -1.10
    几个人
    -1.05
     писать
    -1.04
    erobic
    -1.04
     ciascuno
    -1.02
     needed
    -1.02
    POSITIVE LOGITS
    ׃
    1.18
    らかに
    1.17
    gefügt
    1.13
    zzjoni
    1.08
    λαμβ
    1.06
     vytvoř
    1.06
    esgue
    1.05
     objectAtIndex
    1.05
     intervalo
    1.04
     semillas
    1.02
    Activations Density 0.002%

    No Known Activations