© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19267
    Prev
    Next
    INDEX
    Explanations

    Centers for

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

    The neuron fires on occurrences of “Centers for Disease Control” (and related CDC mentions).

    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
    橚
    -2.81
    𓁹
    -2.31
    𖣘
    -2.20
    🫅
    -2.19
    媜
    -2.19
     respectivos
    -2.17
     inspirada
    -2.11
     tatuagem
    -2.09
    mbgg
    -2.08
     втором
    -2.06
    POSITIVE LOGITS
    焿
    2.84
    with
    2.66
    //
    2.48
    to
    2.39
    銩
    2.30
    ):
    2.28
    袮
    2.19
    卨
    2.16
    Zubereitung
    2.14
    Galería
    2.14
    Activations Density 0.006%

    No Known Activations