© 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. 22-GEMMASCOPE-RES-131K
    7. 79823
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and elements

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

    chemical elements and compounds in scientific notation, especially when presented in formulas.

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

    This neuron fires on chemical element symbols and numeric subscripts/coefficients in formulas.

    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
     paisajes
    -1.26
     après
    -1.25
     souvent
    -1.23
     cuentos
    -1.20
     nieuwe
    -1.20
    揍
    -1.18
     gmina
    -1.14
     estará
    -1.14
     recommande
    -1.13
     laatste
    -1.12
    POSITIVE LOGITS
     []:
    1.28
     When
    1.27
     when
    1.26
    When
    1.21
     Numerous
    1.09
    when
    1.09
    Primeiro
    1.09
    為什麼
    1.07
    ֹת
    1.06
     now
    1.05
    Activations Density 0.005%

    No Known Activations