© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105259
    Prev
    Next
    INDEX
    Explanations

    patriarch | coc | cytochrome

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

    This neuron identifies scientific or religious titles and terms, including "patriarch," "cytochrome," and "coccid" (parts of taxonomic names).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    𓆜
    -3.53
    釭
    -3.30
    y
    -3.14
    their
    -2.86
    橚
    -2.78
    your
    -2.75
    ſſel
    -2.61
    )
    -2.55
    you
    -2.53
    !"
    -2.42
    POSITIVE LOGITS
    的吧
    2.73
    }$
    2.36
     times
    2.33
    的了
    2.23
    みてください
    2.16
    但不
    2.08
    .’”
    2.06
    的那种
    2.03
     několik
    2.03
     elevada
    2.02
    Activations Density 0.011%

    No Known Activations