© 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. 58331
    Prev
    Next
    INDEX
    Explanations

    chemical substitution or doping

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

    This neuron identifies chemical formulas and elemental notations in scientific papers, particularly focusing on materials science and physics literature.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    tagHelperRunner
    -0.86
     '*':
    -0.80
    responseText
    -0.79
    ORS
    -0.78
    NY
    -0.75
    𝐕
    -0.73
     Penggunaan
    -0.73
    merken
    -0.73
    lef
    -0.73
    PU
    -0.72
    POSITIVE LOGITS
     substitution
    1.49
     vacancies
    1.35
     substituting
    1.35
     substitutions
    1.27
    替换
    1.23
     replacement
    1.21
     replacing
    1.20
     vacancy
    1.20
     substituted
    1.13
     replace
    1.12
    Activations Density 0.078%

    No Known Activations