© 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. 47618
    Prev
    Next
    INDEX
    Explanations

    phen compounds and processes

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

    The neuron identifies chemical and scientific terms starting with "phen" like phenol, phenotype, and phenobarbital.

    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
    ↵
    -3.22
     Only
    -2.56
    ?).
    -2.48
    ㉕
    -2.42
     Songtext
    -2.36
     vorigen
    -2.34
     personalmente
    -2.25
    啣
    -2.25
    "},
    -2.22
     sorprend
    -2.22
    POSITIVE LOGITS
    </h2>
    2.75
     мои
    2.44
    {
    2.39
    2
    2.33
     ヶ
    2.30
     }));
    2.22
    \
    2.20
     colorés
    2.19
     животные
    2.14
    他的
    2.11
    Activations Density 0.012%

    No Known Activations