© 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. 8689
    Prev
    Next
    INDEX
    Explanations

    Hidrotic ectodermal dysplasia or PHED office

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

    medical or technical terminology with the "hed" sound, particularly in words like "polyhedra," "sandwiched," and similar endings.

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

    The neuron is strongly activated by any token containing the character sequence “hed” (e.g. HED, –hed endings like sandwiched, dished, ephed, or the Danish nominal suffix –hed).

    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
    .”
    -2.81
    a
    -2.78
    ר
    -2.77
    !”
    -2.63
    ا
    -2.53
    vantaged
    -2.50
    or
    -2.48
    焢
    -2.45
    できる
    -2.39
    豋
    -2.36
    POSITIVE LOGITS
    pecabe
    3.28
    hed
    2.83
     accolades
    2.50
    杁
    2.47
    ,.
    2.34
    廕
    2.20
    掉的
    2.17
     hangout
    2.16
    真心
    2.16
    ',
    2.16
    Activations Density 0.007%

    No Known Activations