© 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. 99413
    Prev
    Next
    INDEX
    Explanations

    python keywords and programming functions

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

    The neuron fires on tokens containing the character sequence “int.”

    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
    </em>
    -2.56
    ,”
    -2.50
    $
    -2.44
    ’
    -2.38
    </h6>
    -2.36
    .”.
    -2.36
    lossians
    -2.30
    इटम
    -2.27
    ).”
    -2.16
     vorigen
    -2.13
    POSITIVE LOGITS
     ſch
    2.63
     sanitario
    2.53
    儅
    2.50
    
    2.39
     querem
    2.27
     creativo
    2.25
     tecnologie
    2.23
     احمد
    2.14
     ritrov
    2.13
     celebrates
    2.11
    Activations Density 0.002%

    No Known Activations