© 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. 54083
    Prev
    Next
    INDEX
    Explanations

    describing states or transitions

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

    The neuron fires on words describing high‐energy pursuit or chase sequences in action scenes.

    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
     things
    -1.96
    ּוֹ
    -1.54
    可以说是
    -1.48
    駅の
    -1.45
     usarlo
    -1.44
     dingen
    -1.42
     :).
    -1.42
    有一定
    -1.41
     development
    -1.40
     preescolar
    -1.40
    POSITIVE LOGITS
    ׇ
    1.33
     no
    1.30
     to
    1.27
     dangere
    1.27
     all
    1.23
    ないので
    1.23
     inapropiados
    1.23
     menikmati
    1.20
     resultat
    1.20
     января
    1.19
    Activations Density 0.037%

    No Known Activations