© 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. 7138
    Prev
    Next
    INDEX
    Explanations

    diseases and treatments

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

    specialized technical or scientific terminology related to specific domains like chemicals, safety, health, energy, and genetics.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     countries
    -0.98
     ifølge
    -0.96
     reconnaît
    -0.94
    子さん
    -0.92
     pozwala
    -0.92
     valgt
    -0.91
     extreme
    -0.91
     gefällt
    -0.90
     metų
    -0.88
     ikkje
    -0.88
    POSITIVE LOGITS
    related
    1.32
    suggested
    1.06
    both
    1.06
    regardless
    1.05
     voren
    0.99
    Răsp
    0.96
     formid
    0.95
     beleid
    0.93
    及其
    0.92
    various
    0.91
    Activations Density 0.222%

    No Known Activations