© 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. 18959
    Prev
    Next
    INDEX
    Explanations

    cryptos, Iron, bifrost, phase

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

    This neuron appears to be entirely inactive—it doesn’t reliably detect or fire on any token patterns.

    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
     other
    -1.87
    ;
    -1.84
     also
    -1.78
    .
    -1.73
     ."
    -1.70
     함께
    -1.66
    mathrm
    -1.61
    </h4>
    -1.61
     assolu
    -1.61
     only
    -1.60
    POSITIVE LOGITS
    里面
    2.00
     —
    1.91
     graciosas
    1.79
    
    1.78
    似乎
    1.75
     gewisse
    1.74
    fi
    1.74
     MOST
    1.70
     améli
    1.70
     momentous
    1.70
    Activations Density 0.087%

    No Known Activations