© 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. 104607
    Prev
    Next
    INDEX
    Explanations

    concepts based on research methods

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

    The neuron activates on content‐bearing technical nouns that name or label research methods, tools, or study components (e.g. “calculations,” “effects,” “study,” “approach,” “tool,” “algorithm,” “parameters,” etc.).

    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
     its
    -1.45
     it
    -1.42
    用
    -1.24
     législation
    -1.18
     성
    -1.17
     его
    -1.14
    把它
    -1.13
     רבה
    -1.13
     zufolge
    -1.13
     Pandey
    -1.13
    POSITIVE LOGITS
    jeux
    1.32
    ่วน
    1.27
    avril
    1.17
    inglés
    1.12
     namely
    1.09
     based
    1.08
     dimana
    1.08
     フロア
    1.06
    Livraison
    1.06
    やかに
    1.06
    Activations Density 0.294%

    No Known Activations