© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102319
    Prev
    Next
    INDEX
    Explanations

    numbers and ranges

    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
     ヌード
    -1.64
     daug
    -1.63
    vorschau
    -1.63
    fertig
    -1.61
    ޤ
    -1.59
    ◆◆
    -1.54
    adakan
    -1.53
    Colore
    -1.52
     himſelf
    -1.52
     作り方
    -1.52
    POSITIVE LOGITS
     only
    2.30
     same
    1.89
    m
    1.88
     biggest
    1.86
     p
    1.78
     maybe
    1.71
    j
    1.70
    w
    1.70
    an
    1.68
    f
    1.68
    Activations Density 0.022%

    No Known Activations