© 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. 85980
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific contexts

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

    The neuron strongly activates on capitalized scientific names and institutions (e.g. Planck, Boltzmann, CSIRO, Monash).

    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
    𐐀
    -2.61
    ’
    -2.45
    </strong>
    -2.34
     unrival
    -2.28
     ganzes
    -2.19
    ჱ
    -2.14
    言う
    -2.11
    滹
    -2.09
    甍
    -2.09
     Sedangkan
    -2.09
    POSITIVE LOGITS
    '
    3.52
    т
    2.78
    </td>
    2.58
    le
    2.38
     några
    2.36
    我的
    2.34
    </
    2.23
    寕
    2.22
    Your
    2.09
     —
    2.05
    Activations Density 0.010%

    No Known Activations