© 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. 101514
    Prev
    Next
    INDEX
    Explanations

    starting segments of various languages

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

    The neuron is detecting Spanish‐ and Portuguese‐language function/content words—especially common adverbs and small words like “nada,” “actualmente,” “mesmo,” “novo,” “poco,” etc.

    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
    咴
    -1.96
    Karakteristik
    -1.95
    ⟝
    -1.90
     essencial
    -1.87
    silueta
    -1.80
    しちゃ
    -1.78
     I
    -1.78
    Waktu
    -1.77
    calidad
    -1.75
    Lokasi
    -1.71
    POSITIVE LOGITS
    .
    2.28
    r
    2.00
    s
    1.92
    in
    1.90
    p
    1.87
    ای
    1.80
    ين
    1.73
    of
    1.69
    ی
    1.66
    ى
    1.60
    Activations Density 0.010%

    No Known Activations