© 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. 22-GEMMASCOPE-RES-131K
    7. 98612
    Prev
    Next
    INDEX
    Explanations

    in locations or conditions

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

    The neuron fires on formal, multi-syllabic content words (especially abstract nouns like involvement, application, fabrication, demonstration, impact, etc.) commonly found in academic or legal prose.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     télécommande
    -1.19
    鮡
    -1.14
    が含ま
    -1.11
     própri
    -1.07
     catedral
    -1.05
     incredi
    -1.05
     autonomie
    -1.04
    ܖ
    -1.03
    がこの
    -1.03
    がとても
    -1.03
    POSITIVE LOGITS
     where
    2.06
    Where
    1.61
     or
    1.60
     Where
    1.55
     besonders
    1.36
     there
    1.29
     gdzie
    1.20
     other
    1.16
     bereits
    1.11
    ﾑ
    1.06
    Activations Density 0.067%

    No Known Activations