© 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. 130354
    Prev
    Next
    INDEX
    Explanations

    animal species and biology

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

    The neuron detects references to animals, particularly in scientific or educational contexts.

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

    This neuron activates on numeric tokens, i.e. numbers and numeric expressions.

    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
    錵
    -2.06
    ᷆
    -1.91
    ಞ
    -1.89
    ᯅ
    -1.81
    ]$
    -1.77
     amarelo
    -1.68
    लिए
    -1.67
     fon
    -1.66
     kakak
    -1.66
    том
    -1.64
    POSITIVE LOGITS
     There
    2.55
     Kollegen
    1.83
     Thus
    1.83
     With
    1.81
     смотреть
    1.80
    </i>
    1.79
     Так
    1.78
     definitive
    1.78
    ("'"
    1.77
     Should
    1.76
    Activations Density 0.036%

    No Known Activations