© 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. 110803
    Prev
    Next
    INDEX
    Explanations

    anaerobic bacteria and processes

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

    This neuron detects terms related to anaerobic microorganisms, fermentation processes, and bacterial environments.

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

    The neuron strongly activates on occurrences of “anaerobic” (and related mentions of anaerobic conditions).

    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
    渽
    -1.67
    ing
    -1.61
    他想
    -1.58
    が付いて
    -1.58
    他才
    -1.56
    光景
    -1.55
    ⎆
    -1.50
    がついて
    -1.46
    身边的
    -1.45
    簠
    -1.45
    POSITIVE LOGITS
    It
    1.73
    }$.
    1.62
    They
    1.50
    }$,
    1.50
    ng
    1.49
     секунд
    1.48
    If
    1.47
    вала
    1.45
    }}=\
    1.44
    }$
    1.40
    Activations Density 0.073%

    No Known Activations