© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86972
    Prev
    Next
    INDEX
    Explanations

    specific nouns following phrases

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

    The neuron is detecting specialized technical or scientific jargon—multi-syllable terms and proper names common in research writing.

    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
     danne
    -1.52
    بدون
    -1.48
    ()!=
    -1.48
    ()/
    -1.47
     poches
    -1.46
     wiz
    -1.44
    已經
    -1.38
    zação
    -1.38
    chalten
    -1.36
     海报
    -1.35
    POSITIVE LOGITS
     in
    2.38
     from
    2.02
     of
    1.92
     can
    1.71
     even
    1.63
     also
    1.60
     for
    1.57
     must
    1.51
     de
    1.48
    不可以
    1.46
    Activations Density 0.095%

    No Known Activations