© 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. 13329
    Prev
    Next
    INDEX
    Explanations

    reef and coral environments

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

    words related to coral reef ecosystems in marine environments.

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

    This neuron primarily activates on mentions of coral‐reef environments (words like “reef,” “corals,” etc.).

    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
    1
    -1.98
    In
    -1.86
    還在
    -1.75
     européens
    -1.73
    整個
    -1.73
     japonais
    -1.66
     necessarie
    -1.66
    wanzig
    -1.64
    噠
    -1.61
    擽
    -1.59
    POSITIVE LOGITS
    </b>
    2.02
    ."
    1.88
     is
    1.81
    ↵
    1.70
    ,"
    1.64
     reefs
    1.61
     '
    1.61
    </h4>
    1.53
     které
    1.48
    、『
    1.45
    Activations Density 0.021%

    No Known Activations