© 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. 66237
    Prev
    Next
    INDEX
    Explanations

    chick followed by embryo, flick, or food

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

    variations of the word "chick" (such as "chicken", "chick-fil-a", "chickadee", or "chickpea").

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

    The neuron detects occurrences of the string “chick” (in any embedding as part of a token).

    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
    <em>
    -2.89
    秝
    -2.64
    .’”
    -2.48
    ཫ
    -2.48
     of
    -2.47
    </sub>
    -2.47
     siete
    -2.47
     religiously
    -2.47
     sogenannten
    -2.45
     painstaking
    -2.45
    POSITIVE LOGITS
    o
    2.72
    Bukan
    2.69
    Rumah
    2.64
    鄖
    2.42
    Sudah
    2.38
    已经
    2.38
    Kenapa
    2.34
    ᠂
    2.34
    ねー
    2.33
    g
    2.33
    Activations Density 0.002%

    No Known Activations