© 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. 48195
    Prev
    Next
    INDEX
    Explanations

    SQL exception

    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
    nickName
    -0.83
    oléon
    -0.79
    никюр
    -0.77
     છ
    -0.77
    henswürdigkeiten
    -0.76
    _{{\
    -0.74
     vật
    -0.74
    риев
    -0.74
    lication
    -0.73
     sekarang
    -0.73
    POSITIVE LOGITS
    Date
    0.89
    Prepared
    0.82
    gna
    0.81
     date
    0.81
    SQLException
    0.80
    日期
    0.77
     SQLException
    0.75
    rtype
    0.74
    ابقة
    0.74
    fita
    0.73
    Activations Density 0.001%

    No Known Activations