© 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. 47534
    Prev
    Next
    INDEX
    Explanations

    education, degrees, and examinations

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

    The neuron flags numeric references to academic qualifications and grade‐level markers (e.g. “matriculation,” “Grade 12,” “XII,” “HSEB”).

    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
    頽
    -1.31
     the
    -1.30
    li
    -1.30
    ve
    -1.30
    ma
    -1.29
    ju
    -1.28
    ねえ
    -1.27
     行き
    -1.25
    før
    -1.24
    たまに
    -1.24
    POSITIVE LOGITS
     cerâmica
    1.46
    drunk
    1.37
     folhe
    1.30
    鷲
    1.27
     pittore
    1.25
     České
    1.24
    aritions
    1.23
    白衣
    1.23
    ancers
    1.23
    愛用
    1.22
    Activations Density 0.013%

    No Known Activations