© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1242
    Prev
    Next
    INDEX
    Explanations

    caption, label, or figure referencing

    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
    newcommand
    -0.82
    ṃ
    -0.82
     ү
    -0.81
    urlencoded
    -0.81
    QApplication
    -0.79
    bardziej
    -0.75
    ète
    -0.74
    still
    -0.74
    =='
    -0.73
    >&
    -0.73
    POSITIVE LOGITS
     labels
    0.93
    그리고
    0.92
     标签
    0.86
     courtesy
    0.81
     label
    0.80
     Absicht
    0.80
     Labels
    0.79
    เพราะ
    0.79
     Floors
    0.79
    子ども
    0.77
    Activations Density 0.002%

    No Known Activations