© 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. 34-GEMMASCOPE-RES-131K
    4. 91196
    Prev
    Next
    INDEX
    Explanations

    Q: technical queries

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

    The neuron fires on Japanese expressions of uncertainty or novice status (e.g. “超初心者です,” “…だと思います,” “初歩的なミス”). It spots phrases where the author admits lack of expertise or hedges their statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     without
    -1.02
    ❣
    -1.00
     when
    -1.00
    🍀
    -1.00
    😻
    -0.97
    irá
    -0.97
    😝
    -0.96
    🤗
    -0.96
     Xx
    -0.96
    😜
    -0.95
    POSITIVE LOGITS
    Twitter
    1.15
     twitter
    1.11
    ১
    1.06
    nteral
    1.04
     Twitter
    1.03
    ってる
    1.00
    fuck
    0.98
     extrêmement
    0.98
    !!!!!!
    0.98
     holy
    0.97
    Activations Density 0.003%

    No Known Activations