© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39470
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

    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
     You
    -2.70
    ፧
    -2.47
    哢
    -2.45
    มัน
    -2.41
    鸫
    -2.39
    ቷ
    -2.33
    鹚
    -2.30
    嗱
    -2.22
     belas
    -2.20
     nového
    -2.16
    POSITIVE LOGITS
    F
    2.89
    E
    2.83
    In
    2.83
    the
    2.73
    '
    2.61
    N
    2.58
    A
    2.52
    1
    2.50
    {
    2.48
    他还
    2.34
    Activations Density 0.044%

    No Known Activations