© 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. 34-GEMMASCOPE-RES-131K
    4. 6911
    Prev
    Next
    INDEX
    Explanations

    .NET Core versions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Comunicação
    -0.91
     Commissione
    -0.84
    參考
    -0.84
     MEMO
    -0.80
    abilit
    -0.78
    immen
    -0.77
     アルバム
    -0.77
    昨日の
    -0.76
     manquante
    -0.76
     该
    -0.75
    POSITIVE LOGITS
     Triple
    0.88
    ु
    0.83
     catfish
    0.81
    camore
    0.74
     cancels
    0.73
     GS
    0.72
    地说道
    0.71
     Spectrum
    0.71
    Triple
    0.69
     Market
    0.68
    Activations Density 0.002%

    No Known Activations