© 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. 13627
    Prev
    Next
    INDEX
    Explanations

    ELISA and proper nouns

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

    proper names including names of people, organizations, places, and scientific tests like ELISA.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to capitalized standalone tokens—like proper names, acronyms, or organization titles.

    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
    寕
    -3.22
    咴
    -2.81
    濊
    -2.72
    憍
    -2.63
    诓
    -2.61
    尐
    -2.58
    梘
    -2.58
    🗹
    -2.56
    缫
    -2.47
    眛
    -2.45
    POSITIVE LOGITS
    </strong>
    3.33
    )
    3.17
    out
    2.89
    是
    2.83
    л
    2.75
    ization
    2.72
    .”
    2.36
    to
    2.31
    ꔹ
    2.28
    of
    2.27
    Activations Density 0.001%

    No Known Activations