© 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. 10-GEMMASCOPE-RES-131K
    7. 45194
    Prev
    Next
    INDEX
    Explanations

    oxygen in chemical reactions

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

    chemical terms related to oxygen and oxidation processes.

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

    The neuron flags technical chemistry contexts, especially occurrences of the chemical element “oxygen” (and related redox/oxidation terms).

    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
    f
    -2.13
    .”
    -2.06
    c
    -1.91
    倘
    -1.83
     to
    -1.59
    u
    -1.59
    l
    -1.56
    </b>
    -1.54
    などで
    -1.53
     Мне
    -1.52
    POSITIVE LOGITS
    }
    1.69
    ̈r
    1.64
     quatre
    1.64
    üsü
    1.51
     бъ
    1.47
     ángeles
    1.45
     dioses
    1.43
     瘦
    1.43
    YNAMIC
    1.42
    knüp
    1.42
    Activations Density 0.094%

    No Known Activations