© 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. 34-GEMMASCOPE-RES-131K
    7. 48217
    Prev
    Next
    INDEX
    Explanations

    price of, Q:, ---

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

    The neuron flags C# XML‐style documentation comment markers (e.g. “///”, “<summary>” and “</summary>”).

    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
     not
    -1.09
     out
    -1.06
     pertaining
    -0.91
     oftentimes
    -0.89
    لاب
    -0.89
     strives
    -0.89
     regarding
    -0.88
     plethora
    -0.87
     goes
    -0.85
     Oeste
    -0.84
    POSITIVE LOGITS
     rapidement
    0.94
     két
    0.93
     Luzon
    0.92
     ウール
    0.90
     подтвер
    0.88
    ⿳
    0.88
     [*]
    0.85
    ドキドキ
    0.84
     sellado
    0.84
    etc
    0.83
    Activations Density 0.001%

    No Known Activations