© 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. 10-GEMMASCOPE-RES-131K
    7. 19900
    Prev
    Next
    INDEX
    Explanations

    abs the word or as part of names

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

    The neuron activates on occurrences of the standalone token “abs” (e.g. the abs function or an “abs” variable) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    撄
    -3.64
    诹
    -3.19
    腚
    -3.11
     แต่
    -3.06
    儅
    -2.95
    鮰
    -2.89
     ſmall
    -2.86
    
    -2.83
    薜
    -2.78
    ⟣
    -2.75
    POSITIVE LOGITS
    1
    4.66
    9
    4.44
    2
    4.44
    3
    4.25
    To
    3.78
    8
    3.75
    7
    3.73
    4
    3.63
    In
    3.44
    At
    3.44
    Activations Density 0.004%

    No Known Activations