© 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. 59862
    Prev
    Next
    INDEX
    Explanations

    technical terms

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

    The neuron strongly activates on specialized, often multi‐syllabic technical or domain-specific nouns and compound morphological roots.

    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
     in
    -1.59
    מת
    -1.38
     which
    -1.34
     on
    -1.34
     than
    -1.31
     '',
    -1.27
     カスタム
    -1.27
     with
    -1.27
     \%$,
    -1.25
    "")
    -1.25
    POSITIVE LOGITS
     vielleicht
    1.52
     Bahkan
    1.41
     veía
    1.39
     erzä
    1.34
     atractiva
    1.34
     Setelah
    1.33
     llamaba
    1.30
     Selain
    1.29
     góry
    1.27
     Tetapi
    1.26
    Activations Density 0.255%

    No Known Activations