© 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. 112669
    Prev
    Next
    INDEX
    Explanations

    chlorophyll and related compounds

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

    The neuron detects chlorophyll and related plant pigment terms in scientific contexts.

    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_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
    er
    -2.30
    s
    -2.16
     или
    -2.14
    慊
    -2.14
    焢
    -2.11
    銥
    -1.96
    en
    -1.92
    𓄹
    -1.88
     These
    -1.87
    鉭
    -1.85
    POSITIVE LOGITS
    <td>
    2.02
     gröss
    1.95
    .
    1.84
     männer
    1.80
     أيض
    1.76
    ╕
    1.73
    神
    1.73
    是我的
    1.69
    是個
    1.67
    是想
    1.64
    Activations Density 0.008%

    No Known Activations