© 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. 10-GEMMASCOPE-RES-131K
    7. 90283
    Prev
    Next
    INDEX
    Explanations

    anion, oxide, fluoride

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

    chemical formulas and ion notations, particularly anions and charged molecules.

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

    The neuron fires on chemical formulas for ions and other charged species (e.g. NO₃⁻, CO₃²⁻, Cl⁻, O₂, acetate anion).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     their
    -1.68
     enables
    -1.48
    ть
    -1.48
     some
    -1.45
     enable
    -1.43
     there
    -1.42
     if
    -1.40
     émission
    -1.40
     kümmern
    -1.40
    tamentos
    -1.39
    POSITIVE LOGITS
     of
    2.13
     ameryka
    1.58
     naszym
    1.48
     sapere
    1.48
     decidedly
    1.44
     exceedingly
    1.41
     vrijdag
    1.40
     dezelve
    1.39
     registrados
    1.39
     kwa
    1.38
    Activations Density 0.052%

    No Known Activations