© 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. 130547
    Prev
    Next
    INDEX
    Explanations

    initialization code and xml attributes

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

    The neuron fires on occurrences of “Initialize” (e.g. the ISupportInitialize.BeginInit/EndInit calls).

    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
    籥
    -1.42
    いましたが
    -1.41
     guardado
    -1.38
    買う
    -1.34
     одном
    -1.34
    hlander
    -1.32
    by
    -1.32
    da
    -1.31
     cairan
    -1.31
     необходи
    -1.30
    POSITIVE LOGITS
    </strong>
    2.03
    0
    1.70
    鱨
    1.69
    锇
    1.46
    ulgação
    1.45
     &
    1.44
     that
    1.41
     of
    1.41
    pedidos
    1.41
    cartas
    1.40
    Activations Density 0.015%

    No Known Activations