© 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. 57559
    Prev
    Next
    INDEX
    Explanations

    code structure and errors

    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
     to
    -1.42
     new
    -1.34
     Now
    -1.33
    3
    -1.32
     Tieren
    -1.24
    2
    -1.15
    elif
    -1.13
     will
    -1.13
     possono
    -1.12
     can
    -1.11
    POSITIVE LOGITS
    姿勢
    1.29
    高端
    1.27
    形势
    1.21
    )
    1.21
     mediante
    1.21
     ibang
    1.18
    อื่น
    1.15
    obt
    1.14
    achieved
    1.14
     compris
    1.13
    Activations Density 0.149%

    No Known Activations