© 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. 67693
    Prev
    Next
    INDEX
    Explanations

    Intent creation

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

    The neuron fires on numeric literal tokens (e.g. integer or floating‐point constants) in code snippets.

    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
    </h3>
    -2.05
      
    -1.88
    </h2>
    -1.78
     $
    -1.66
    </blockquote>
    -1.64
    $
    -1.51
     Different
    -1.50
     após
    -1.50
     sees
    -1.45
     was
    -1.45
    POSITIVE LOGITS
     которы
    1.70
     Sangat
    1.63
     vader
    1.56
     navide
    1.49
    atnya
    1.45
    parently
    1.45
     taxe
    1.45
     Joaqu
    1.44
    tempts
    1.42
     słucha
    1.42
    Activations Density 0.004%

    No Known Activations