© 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. 65305
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and elements

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

    chemical formulas and mathematical equations.

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

    The neuron strongly activates on chemical‐formula and reaction tokens (element symbols, stoichiometric numbers, plus signs, arrows, etc.), i.e. parts of chemical equations.

    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
     which
    -1.17
     that
    -1.13
    vidade
    -1.12
     oku
    -1.09
     habis
    -1.07
     slad
    -1.06
     sagrada
    -1.05
     situe
    -1.04
     autora
    -1.03
    гласно
    -1.02
    POSITIVE LOGITS
     dior
    1.20
     lakers
    1.09
     Moderately
    1.07
     batman
    1.06
     charlotte
    1.05
     Exquisite
    1.03
     Envi
    1.02
     手順
    1.02
     witcher
    1.02
     garmin
    1.02
    Activations Density 0.005%

    No Known Activations