© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59939
    Prev
    Next
    INDEX
    Explanations

    chemical elements and compounds

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

    chemical elements and compounds, particularly gallium and other metals used in semiconductors and electronic materials.

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

    This neuron detects chemical element and compound names, especially semiconductor materials (e.g. gallium, indium, alloys, III-V compounds).

    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
    _
    -2.31
    }$
    -1.98
    </sub>
    -1.93
    </sup>
    -1.73
    """
    -1.61
     "";
    -1.59
    ENIA
    -1.56
    <h2>
    -1.55
    多くの
    -1.54
    ("
    -1.52
    POSITIVE LOGITS
     When
    1.84
     Sometimes
    1.74
    铋
    1.59
    StoryboardSegue
    1.53
    %")
    1.53
    辄
    1.51
    骉
    1.51
    桄
    1.49
     Cuando
    1.49
    棪
    1.48
    Activations Density 0.030%

    No Known Activations