© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85926
    Prev
    Next
    INDEX
    Explanations

    activities and consumption

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

    The neuron activates on verbs describing people engaging in activities (e.g., watch, play, shoot, wear).

    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
    komsten
    -1.52
     should
    -1.48
    From
    -1.41
     fön
    -1.40
    古风
    -1.34
     respekt
    -1.31
    Through
    -1.30
    phoric
    -1.30
    }$,
    -1.28
     عليك
    -1.27
    POSITIVE LOGITS
     a
    1.83
    idk
    1.77
    didn
    1.70
    wasn
    1.65
    seems
    1.49
    出了一
    1.46
     to
    1.45
    weren
    1.45
    着一
    1.43
     indivíduo
    1.38
    Activations Density 0.285%

    No Known Activations