© 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. 127415
    Prev
    Next
    INDEX
    Explanations

    upon

    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
    because
    -1.70
     because
    -1.63
     However
    -1.47
    Because
    -1.45
     consisting
    -1.41
     пам
    -1.41
     which
    -1.38
    When
    -1.33
     taking
    -1.33
     beautiful
    -1.30
    POSITIVE LOGITS
     เก็
    1.43
    yled
    1.38
     uy
    1.35
    🔺
    1.34
     hade
    1.34
     exemple
    1.34
    ⅖
    1.34
    Phaser
    1.33
     strikingly
    1.33
     REALLY
    1.33
    Activations Density 18.458%

    No Known Activations