© 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. 90809
    Prev
    Next
    INDEX
    Explanations

    hen, chicken, rooster

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

    The main thing this neuron does is detect references to chickens or related poultry terms (e.g., chicken, chickens, hen, eggs).

    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
     that
    -2.13
     really
    -1.56
    ↵↵
    -1.49
    u
    -1.45
     what
    -1.44
     undangan
    -1.42
     from
    -1.41
     changes
    -1.40
     how
    -1.38
    What
    -1.38
    POSITIVE LOGITS
    茈
    1.75
     adatt
    1.55
    ícias
    1.48
     We
    1.46
     Nachdem
    1.43
     извест
    1.41
    iteľ
    1.39
    去找
    1.38
    骉
    1.38
     Това
    1.36
    Activations Density 0.010%

    No Known Activations