© 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. 34-GEMMASCOPE-RES-131K
    7. 109340
    Prev
    Next
    INDEX
    Explanations

    some help

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

    The neuron activates on descriptive qualifier words—especially adjectives and adverbs that specify or emphasize attributes (e.g. “technical,” “important,” “useful,” “rich,” “many,” 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_34/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
     superbes
    -0.92
     périodes
    -0.89
     qualités
    -0.88
     mêmes
    -0.85
     getHeight
    -0.83
     leçons
    -0.82
    ТИ
    -0.82
     pensées
    -0.82
     tâches
    -0.82
     preuves
    -0.81
    POSITIVE LOGITS
     initiatives
    1.07
     remarks
    1.04
    equilibrium
    0.94
     considerations
    0.93
     licencias
    0.91
     proposals
    0.90
     inconven
    0.88
     hypotheses
    0.87
    ichert
    0.87
     curious
    0.86
    Activations Density 0.035%

    No Known Activations