© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78376
    Prev
    Next
    INDEX
    Explanations

    activity and descriptors

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

    This neuron is highly activated by the word “activity” (and its variants, e.g. “Activities” or “ActivityIndicator”).

    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
    raulic
    -1.24
    isation
    -1.24
     letech
    -1.13
    peel
    -1.09
     adherence
    -1.09
     unveiling
    -1.08
     exceedingly
    -1.05
     alça
    -1.05
    ⑾
    -1.04
     capitán
    -1.02
    POSITIVE LOGITS
    activity
    1.71
     undertaken
    1.46
    Activities
    1.34
    activities
    1.30
     getActivity
    1.30
     activity
    1.27
     activities
    1.26
    Activity
    1.24
     ACTIVITIES
    1.21
     Activity
    1.19
    Activations Density 0.035%

    No Known Activations