© 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. 66607
    Prev
    Next
    INDEX
    Explanations

    storing in an array

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

    The neuron fires on numeric literals (both integers and decimals) appearing in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    phrases describing data being stored in arrays or collections.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    phrases that describe placing or storing something into a container or location (e.g., data being put in/into/on a target such as a structure or UI).

    oai_token-act-pair · gpt-5Triggered 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
    M
    -1.13
    での
    -1.12
    すべての
    -1.11
     whereas
    -1.11
    がなく
    -1.10
    全ての
    -1.10
    髌
    -1.10
     estando
    -1.07
    盉
    -1.06
     tandis
    -1.05
    POSITIVE LOGITS
     a
    1.86
     our
    1.62
     their
    1.56
     an
    1.55
     perusahaan
    1.35
     kabát
    1.34
     in
    1.28
     seolah
    1.27
     several
    1.27
     mengalir
    1.25
    Activations Density 0.107%

    No Known Activations