© 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. 34-GEMMASCOPE-RES-131K
    7. 82304
    Prev
    Next
    INDEX
    Explanations

    metal alchemy and chemistry

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

    titles or named entities within technical or informational content.

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

    The neuron fires strongly on document headings or titles—particularly multiword proper-noun phrases (e.g. film or article titles) and other section headings.

    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
     Schwal
    -0.77
     informée
    -0.72
    Computers
    -0.71
     dựng
    -0.71
     universitaire
    -0.67
    getInt
    -0.67
     asymptotic
    -0.66
     afresh
    -0.66
    icose
    -0.66
    おしゃれ
    -0.66
    POSITIVE LOGITS
     trans
    1.51
     alchemy
    1.32
     alchemist
    1.07
     Mustang
    1.05
     Alchemy
    1.01
    trans
    1.01
    錬
    1.01
    Alchemy
    0.95
     Alchemist
    0.91
     Trans
    0.91
    Activations Density 0.010%

    No Known Activations