© 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. 129940
    Prev
    Next
    INDEX
    Explanations

    limits and sequences involving x, n, or T

    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
    environnement
    -1.64
    Lleg
    -1.63
    騮
    -1.58
    Nadie
    -1.52
    Bajo
    -1.46
     vacunas
    -1.46
    ᐠ
    -1.46
     perché
    -1.45
    ࿚
    -1.43
    次に
    -1.42
    POSITIVE LOGITS
    .
    1.73
    THIS
    1.54
     this
    1.50
    ير
    1.47
    ="
    1.46
    this
    1.44
    \
    1.40
     هذا
    1.35
     podemos
    1.33
     toutefois
    1.33
    Activations Density 0.005%

    No Known Activations