© 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. 58433
    Prev
    Next
    INDEX
    Explanations

    times higher, multiplies, or compares magnitude

    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
     mondeo
    -1.45
    ”?
    -1.41
     moldura
    -1.40
     первом
    -1.38
    ”,
    -1.35
     pata
    -1.32
    ”(
    -1.32
    妺
    -1.31
    项目的
    -1.31
    ”).
    -1.30
    POSITIVE LOGITS
    不同
    1.49
     diferentes
    1.47
     '
    1.37
     olika
    1.25
     různých
    1.21
    different
    1.20
    ↵
    1.20
     "
    1.16
     bedeut
    1.16
    various
    1.14
    Activations Density 0.092%

    No Known Activations