© 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. 11047
    Prev
    Next
    INDEX
    Explanations

    code keywords

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

    The neuron fires on bracket-based property or array lookups (e.g. the “[…]” notation used to access keys).

    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
     voľ
    -1.23
     časti
    -1.23
    extremely
    -1.20
    those
    -1.15
    なども
    -1.12
    aner
    -1.10
     flera
    -1.09
     starten
    -1.09
     magnifique
    -1.09
    Географи
    -1.09
    POSITIVE LOGITS
     is
    1.35
     time
    1.33
     by
    1.29
     without
    1.23
     payment
    1.16
     made
    1.15
     like
    1.14
     (
    1.14
     include
    1.13
     demanded
    1.13
    Activations Density 0.006%

    No Known Activations