© 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. 10-GEMMASCOPE-RES-131K
    7. 66217
    Prev
    Next
    INDEX
    Explanations

    probate and transverse

    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
    g
    -2.70
     {
    -2.64
    ні
    -2.31
    鏷
    -2.30
    甞
    -2.30
    的
    -2.25
     '
    -2.22
    ed
    -2.17
     ´
    -2.14
    s
    -2.14
    POSITIVE LOGITS
    AutoresizingMask
    2.72
    ｑ
    2.48
    趼
    2.45
    ｘ
    2.41
     összefoglaló
    2.36
     “,
    2.23
    ),”
    2.23
    谙
    2.22
    逦
    2.22
    ！）
    2.20
    Activations Density 0.013%

    No Known Activations