© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40225
    Prev
    Next
    INDEX
    Explanations

    run of dominance or high temperatures

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

    The neuron detects numeric statistical phrases describing runs, streaks, strings, counts, or similar record‐style measures.

    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
    .
    -1.53
     both
    -1.52
     reason
    -1.38
    曠
    -1.37
    饪
    -1.31
    んびり
    -1.30
    羈
    -1.29
    
    -1.28
    驟
    -1.28
    edoria
    -1.28
    POSITIVE LOGITS
     principalmente
    1.43
    こちらの
    1.42
    （※
    1.41
     ambiti
    1.41
     ravis
    1.40
    stappen
    1.38
    Dicas
    1.36
    ClInclude
    1.34
     realmente
    1.34
    噲
    1.34
    Activations Density 0.053%

    No Known Activations