© 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. 42837
    Prev
    Next
    INDEX
    Explanations

    cooperating, synergistic, assist, cofactor

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

    The neuron primarily activates for the term "cofactor" and words related to cooperation and synergy in scientific or technical contexts.

    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
    бираем
    -1.77
    '
    -1.76
    跸
    -1.64
    閦
    -1.63
    谖
    -1.59
    ໊
    -1.57
     diminishes
    -1.55
     fortalec
    -1.55
     hué
    -1.53
    moderne
    -1.51
    POSITIVE LOGITS
    </b>
    1.81
     мог
    1.70
    All
    1.68
     fliegen
    1.68
    ی
    1.63
    The
    1.60
    }$.
    1.58
     Also
    1.55
    ではでは
    1.52
     n
    1.51
    Activations Density 0.010%

    No Known Activations