© 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. 22-GEMMASCOPE-RES-131K
    7. 15599
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

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

    technical measurements or specifications in scientific and technical contexts.

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

    This neuron selectively lights up on content-bearing technical keywords (specialized nouns or verbs) that signal the main topic or subject matter of a passage.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     alimenti
    -1.08
     inadequate
    -0.93
    ല്ല
    -0.88
     celebrating
    -0.86
    olescence
    -0.86
     diverso
    -0.85
     membri
    -0.85
     mwaka
    -0.85
     adequate
    -0.84
     merav
    -0.84
    POSITIVE LOGITS
     and
    1.34
     naše
    1.08
     filosofía
    1.06
     izdel
    1.04
    жные
    1.04
     vaše
    1.02
    想了
    1.01
     cechy
    0.96
     obrazy
    0.95
     getItemCount
    0.94
    Activations Density 0.105%

    No Known Activations