© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84089
    Prev
    Next
    INDEX
    Explanations

    programming keywords

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

    The neuron lights up on code‐like tokens—especially identifiers, function or method names, and element IDs in programming 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_22/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
     is
    -1.05
    すぐに
    -0.96
    จึง
    -0.95
    That
    -0.93
    \
    -0.92
    同様に
    -0.91
    それが
    -0.91
    <em>
    -0.90
     immorality
    -0.90
     также
    -0.89
    POSITIVE LOGITS
    corrhi
    1.20
     gantung
    1.19
    näm
    1.18
    ">!
    1.16
     Matériau
    1.16
     sélectionnés
    1.15
     patate
    1.15
    。」
    1.15
     .
    1.13
    ometry
    1.13
    Activations Density 0.022%

    No Known Activations