© 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. 10-GEMMASCOPE-RES-131K
    7. 19535
    Prev
    Next
    INDEX
    Explanations

    multilingual algorithm precursors

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

    The neuron spikes on vague or interrogative pronouns (e.g. “algo,” “do,” “estos,” “wat”) across Spanish, Portuguese, and English.

    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
    m
    -3.19
    枼
    -2.75
    -
    -2.70
    🡺
    -2.55
    
    -2.42
    跸
    -2.38
    pecabe
    -2.38
    者的
    -2.27
    戋
    -2.25
    湏
    -2.23
    POSITIVE LOGITS
     was
    2.27
     \
    2.23
    ！"
    2.20
     Pastikan
    2.16
    These
    2.14
    沒有
    2.14
     solchen
    2.11
    ほんと
    2.11
    混乱
    2.09
    With
    2.06
    Activations Density 0.002%

    No Known Activations