© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99299
    Prev
    Next
    INDEX
    Explanations

    acetylase, maritime, permafrost, jack of all trades

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

    enzyme names and technical biological/chemical terms, particularly focusing on enzymes like 'deacetylases' and similar scientific terminology.

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

    The neuron consistently lights up on longer, relatively rare content words (especially multi-syllabic technical or key nouns/verbs).

    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
     tristesse
    -1.48
    fő
    -1.48
     bonitos
    -1.45
    轼
    -1.38
    を書いて
    -1.37
    Q
    -1.33
     saisons
    -1.31
     Comes
    -1.30
    ⮑
    -1.30
    噥
    -1.29
    POSITIVE LOGITS
    ot
    1.67
    5
    1.67
    ↵↵↵
    1.59
    iliares
    1.58
     or
    1.51
     bądź
    1.43
    ↵↵↵↵
    1.42
    '])){
    1.41
    ']));
    1.41
    ous
    1.39
    Activations Density 0.074%

    No Known Activations