© 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. 10-GEMMASCOPE-RES-131K
    4. 21961
    Prev
    Next
    INDEX
    Explanations

    code elements and international words

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

    This neuron never produces a non-zero activation on any token here, i.e. it doesn’t detect any consistent pattern in these examples.

    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
    鼍
    -2.34
     parachoque
    -2.31
    鸶
    -2.11
    脔
    -2.08
    蛩
    -2.06
    珰
    -1.97
    泔
    -1.95
     vinil
    -1.92
    besondere
    -1.89
    雠
    -1.87
    POSITIVE LOGITS
     in
    2.38
    ケモン
    1.99
     and
    1.95
    with
    1.76
     appunto
    1.73
    </h3>
    1.72
    مية
    1.70
    ̓
    1.65
     gerçekten
    1.64
    fledged
    1.60
    Activations Density 0.008%

    No Known Activations