© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44201
    Prev
    Next
    INDEX
    Explanations

    marine life and seafood

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

    names of marine animals and seafood.

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

    The neuron detects mentions of marine animals—especially seafood invertebrates like lobsters, oysters, sea cucumbers, snails, 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
    蹕
    -1.88
    镦
    -1.84
     selalu
    -1.78
    栻
    -1.78
    魠
    -1.76
     définiti
    -1.73
     Tämä
    -1.72
     Tiga
    -1.70
    
    -1.68
     CRIST
    -1.67
    POSITIVE LOGITS
     et
    2.06
     einem
    1.97
    ll
    1.88
     ‘
    1.72
     scallops
    1.69
    n
    1.69
     viagra
    1.68
     annoying
    1.67
    </i>
    1.63
     {
    1.61
    Activations Density 0.002%

    No Known Activations