© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112363
    Prev
    Next
    INDEX
    Explanations

    abstract section

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

    This neuron detects occurrences of the term “abstract” (and its variants like “abstracts”) in document headers or metadata sections.

    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
     you
    -1.90
     I
    -1.77
     alguns
    -1.73
    莇
    -1.66
    蓠
    -1.66
     poderia
    -1.65
    ка
    -1.63
     who
    -1.59
    也都
    -1.59
     The
    -1.59
    POSITIVE LOGITS
     diminish
    1.58
    见识
    1.57
     superbly
    1.54
    Both
    1.51
    伱
    1.49
     unrelenting
    1.49
    इटम
    1.47
     perpetually
    1.47
     newly
    1.46
     unparalleled
    1.46
    Activations Density 0.027%

    No Known Activations