© 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. 11109
    Prev
    Next
    INDEX
    Explanations

    specific noun concepts

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

    The neuron activates on specialized nouns or domain-specific technical terms (e.g. names of fields, methodologies, or formal concepts).

    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
    estaw
    -1.65
    粜
    -1.54
    still
    -1.47
    ilding
    -1.47
    chsel
    -1.46
    の高い
    -1.44
     («
    -1.43
     タンク
    -1.42
     à
    -1.41
     inconvénients
    -1.40
    POSITIVE LOGITS
     also
    2.09
     and
    2.06
     even
    2.02
     especially
    1.72
     bahkan
    1.63
     zarówno
    1.53
     Also
    1.49
     just
    1.47
     more
    1.46
     murieron
    1.45
    Activations Density 0.821%

    No Known Activations