© 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. 18999
    Prev
    Next
    INDEX
    Explanations

    followed by a role or organization

    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
     which
    -2.31
     whose
    -1.93
     with
    -1.88
     waarvan
    -1.52
     that
    -1.52
     outstanding
    -1.49
     sayfası
    -1.48
    最早
    -1.46
     and
    -1.45
     Wissenschaften
    -1.40
    POSITIVE LOGITS
    ere
    1.65
     need
    1.59
     और
    1.53
    6
    1.52
    not
    1.50
     izquierdo
    1.48
    ⦊
    1.46
    圌
    1.46
    鹟
    1.46
    無料で
    1.46
    Activations Density 0.042%

    No Known Activations