© 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. 22-GEMMASCOPE-RES-131K
    7. 38944
    Prev
    Next
    INDEX
    Explanations

    task of, Tag Archives, Quantum Zeno, Does matrix

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

    The neuron responds to abstract nouns and verbs that denote duties, services, or functional roles (e.g. “have,” “task,” “offerings”).

    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
     three
    -1.92
     eight
    -1.84
     two
    -1.83
     seven
    -1.77
     nine
    -1.74
     only
    -1.72
     four
    -1.71
     five
    -1.70
     six
    -1.63
     those
    -1.57
    POSITIVE LOGITS
     your
    2.09
     you
    1.66
    kün
    1.44
    adakan
    1.41
    }
    1.41
    Puedes
    1.39
    你们
    1.37
     вашу
    1.36
     yourself
    1.36
     ‌
    1.34
    Activations Density 0.000%

    No Known Activations