© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59317
    Prev
    Next
    INDEX
    Explanations

    dams and water structures

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

    The neuron fires strongly on mentions of water‐control structures (e.g., breakwaters, dams, reservoirs).

    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
    ꯳
    -1.63
    
    -1.62
    Елена
    -1.54
    Because
    -1.52
    of
    -1.48
    Ирина
    -1.48
    Юлия
    -1.46
     bekan
    -1.45
    Encu
    -1.45
    Crítica
    -1.44
    POSITIVE LOGITS
    </b>
    1.88
    >
    1.77
    </u>
    1.74
    </code>
    1.59
    </sub>
    1.53
    '
    1.52
     "
    1.48
     to
    1.44
     spart
    1.44
     самый
    1.42
    Activations Density 0.010%

    No Known Activations