© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30980
    Prev
    Next
    INDEX
    Explanations

    verb "to be" plus predicate adjective/adverb

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    cherichia
    -1.14
     psicología
    -1.13
    finanz
    -1.13
    bereiche
    -1.11
    衕
    -1.11
    より
    -1.08
    ológico
    -1.05
    秶
    -1.05
    anko
    -1.04
     FILED
    -1.03
    POSITIVE LOGITS
     औसत
    0.92
     οποία
    0.92
    🥂
    0.85
    🫶
    0.84
     कथ
    0.83
    桅
    0.83
    alcool
    0.82
     САД
    0.82
     还
    0.81
    为何
    0.81
    Activations Density 0.208%

    No Known Activations