© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71181
    Prev
    Next
    INDEX
    Explanations

    personalmedicalfoodskills

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

    terms related to specialized technical or medical vocabulary.

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

    This neuron fires strongly on isolated, topic‐defining nouns (often section headings or key subject terms) across a variety of technical 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_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
     gastron
    -0.94
     особли
    -0.90
    ánea
    -0.87
     marmor
    -0.87
     чёр
    -0.85
     tampon
    -0.85
     exchanging
    -0.84
    OnInit
    -0.84
     fasc
    -0.82
    IDGE
    -0.81
    POSITIVE LOGITS
     personal
    1.09
    jogador
    1.09
     agréable
    1.06
    lahir
    1.05
     such
    1.02
     wellbeing
    1.02
     pessoal
    1.01
     Personal
    0.99
     keselamatan
    0.98
    lampu
    0.96
    Activations Density 0.134%

    No Known Activations