© 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. 40052
    Prev
    Next
    INDEX
    Explanations

    history

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

    The neuron specifically fires on occurrences of the word “History,” as in section headings or labels.

    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
     considéré
    -2.55
    ⩴
    -2.45
     récemment
    -2.23
    越是
    -2.20
     utilizados
    -2.17
     vielleicht
    -2.13
    苳
    -2.13
    ↵↵
    -2.13
    ඍ
    -2.11
     asesin
    -2.09
    POSITIVE LOGITS
    墻
    2.58
     \
    2.47
     gången
    2.41
    ↵
    2.38
    ဴ
    2.36
    {
    2.28
    ┿
    2.23
    ጵ
    2.22
    𝔗
    2.22
    le
    2.13
    Activations Density 0.035%

    No Known Activations