© 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. 48490
    Prev
    Next
    INDEX
    Explanations

    peer review and academic journals

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

    phrases indicating peer-reviewed academic publications or journals.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on mentions of peer-reviewed (or review) publication contexts.

    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
     are
    -2.59
    .
    -1.86
     ‘
    -1.61
    );
    -1.55
     was
    -1.53
    So
    -1.50
     utilise
    -1.50
     to
    -1.48
     V
    -1.46
    ’,
    -1.43
    POSITIVE LOGITS
     garçons
    2.00
     médecins
    1.91
    靣
    1.86
     bordados
    1.81
     conductores
    1.80
     véritables
    1.80
     bekasi
    1.79
    凇
    1.74
     diseñadores
    1.72
     bébés
    1.71
    Activations Density 0.011%

    No Known Activations