© 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. 10-GEMMASCOPE-RES-131K
    7. 29129
    Prev
    Next
    INDEX
    Explanations

    affirmation of correctness

    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_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
    \\
    -2.48
     have
    -2.11
    甃
    -2.09
    }
    -2.08
    {
    -1.98
     be
    -1.95
     For
    -1.95
    
    -1.95
    da
    -1.93
    QMetaType
    -1.93
    POSITIVE LOGITS
    ↵
    2.70
     Mehrheit
    2.25
    ･･
    2.11
    Ⲉ
    2.09
    疍
    2.08
    身边的
    2.06
     ceket
    2.03
     جذب
    1.99
    お値段
    1.97
    CHREIB
    1.97
    Activations Density 0.015%

    No Known Activations