© 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. 19260
    Prev
    Next
    INDEX
    Explanations

    conditions needed beforehand

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

    The neuron activates on occurrences of the word “prerequisite” (or “prerequisites”)—typically in course or section headings.

    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
    1
    -2.89
    4
    -2.84
    2
    -2.84
    -
    -2.83
    or
    -2.81
    {
    -2.80
    )
    -2.77
     "
    -2.77
    9
    -2.75
    "
    -2.69
    POSITIVE LOGITS
    ‪.‬‬
    3.27
    哢
    3.05
    ⢓
    2.88
    鈇
    2.67
    ～。
    2.52
    最后由
    2.52
    霂
    2.42
    ”،
    2.42
    Ꞓ
    2.39
     sosteniendo
    2.38
    Activations Density 0.001%

    No Known Activations