© 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. 39980
    Prev
    Next
    INDEX
    Explanations

    batch file operations

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

    The neuron specifically fires on occurrences of the word “batch.”

    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
    ↵↵
    -2.73
    ן
    -2.23
     .
    -2.23
     kulinar
    -2.19
    gelegt
    -2.11
    咔嚓
    -2.08
    𐐀
    -2.06
     vierte
    -2.02
     hilos
    -2.00
     ſever
    -1.96
    POSITIVE LOGITS
    y
    3.84
    section
    2.86
    2
    2.78
    s
    2.64
    3
    2.61
     BOTH
    2.59
     annat
    2.53
    o
    2.45
     the
    2.38
    </b>
    2.36
    Activations Density 0.015%

    No Known Activations