© 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. 10-GEMMASCOPE-RES-131K
    7. 11686
    Prev
    Next
    INDEX
    Explanations

    also [verb]

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

    The neuron spots third‐person singular present‐tense verbs (e.g. “depends,” “acts,” “evolves,” “runs,” “employs,” “is subject to,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     also
    -2.52
     only
    -1.83
     even
    -1.77
     again
    -1.59
     zarówno
    -1.55
     just
    -1.53
     it
    -1.53
     også
    -1.52
     both
    -1.52
     either
    -1.48
    POSITIVE LOGITS
     other
    1.69
     inkluder
    1.44
    ことから
    1.43
     include
    1.37
    Gruss
    1.35
     zonder
    1.34
     innych
    1.34
    беріга
    1.34
    nesto
    1.34
     esfuer
    1.34
    Activations Density 0.516%

    No Known Activations