© 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. 34-GEMMASCOPE-RES-131K
    7. 106940
    Prev
    Next
    INDEX
    Explanations

    chemical bonds and reactions

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

    chemical bonds represented by the notation C-H, C=C, or similar chemical structure symbols in scientific text.

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

    The neuron detects numeric tokens and numeric expressions (e.g. numbers, numerical ranges, and quantities).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     లే
    -0.74
    レッ
    -0.74
    нрави
    -0.73
     Bouchard
    -0.73
    Rispondi
    -0.72
    uitton
    -0.70
    ounding
    -0.69
    öhe
    -0.69
     peruano
    -0.69
    ابی
    -0.69
    POSITIVE LOGITS
     vs
    1.20
     versus
    1.02
     Vs
    0.93
     VS
    0.88
    宙
    0.79
     Psi
    0.77
    –
    0.75
    vs
    0.73
    inglés
    0.72
     Mgr
    0.71
    Activations Density 0.061%

    No Known Activations