© 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. 34-GEMMASCOPE-RES-131K
    7. 57144
    Prev
    Next
    INDEX
    Explanations

    `cellForRowAtIndexPath`

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

    The neuron activates on programming‐language identifiers—especially CamelCase class and method names (e.g. UITableViewCell, tableView:cellForRowAtIndexPath:)—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_34/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
     teater
    -1.08
    💀
    -0.93
     corrom
    -0.90
    дове
    -0.90
     tarda
    -0.88
     gabri
    -0.88
     gruppe
    -0.88
     lanka
    -0.86
     Liban
    -0.86
     sapat
    -0.84
    POSITIVE LOGITS
     of
    0.90
     at
    0.89
    AKERS
    0.80
     row
    0.80
     estarán
    0.79
     mildew
    0.79
    getRow
    0.76
     magnified
    0.75
     ju
    0.75
    although
    0.75
    Activations Density 0.008%

    No Known Activations