© 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. 42760
    Prev
    Next
    INDEX
    Explanations

    naval vessels

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

    This neuron detects mentions of naval vessel classes or ship type designations (e.g. frigate, destroyer, submarine chaser).

    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
    ilets
    -1.27
     ولكن
    -1.14
    wnątrz
    -1.07
    Người
    -1.05
     téléph
    -1.05
    atste
    -1.03
    𝐉
    -1.02
    浼
    -1.00
     julka
    -1.00
     regal
    -1.00
    POSITIVE LOGITS
     it
    1.33
     to
    1.27
    hadores
    1.16
     zama
    1.09
    ซ์
    1.09
     yakni
    1.09
    cans
    1.09
    drawSprites
    1.08
    ("")]
    1.08
    cluding
    1.05
    Activations Density 0.080%

    No Known Activations