© 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. 10723
    Prev
    Next
    INDEX
    Explanations

    medium.com articles

    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
    1
    -2.30
     lament
    -2.30
     ‘‘
    -2.23
    {
    -2.08
     senza
    -2.03
    I
    -2.03
    2
    -2.02
    ライム
    -2.02
     erneu
    -2.00
    M
    -1.98
    POSITIVE LOGITS
    し
    2.30
     folos
    2.13
    翾
    2.03
     demostrar
    1.95
     \&
    1.91
     asegurar
    1.89
    胪
    1.88
    this
    1.86
    сіб
    1.86
     děti
    1.81
    Activations Density 0.007%

    No Known Activations