© 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. 22-GEMMASCOPE-RES-131K
    7. 34902
    Prev
    Next
    INDEX
    Explanations

    digits, unsigned, int, live

    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_22/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
     disponib
    -1.06
    这些
    -1.02
     cả
    -0.96
    這些
    -0.91
     —
    -0.91
     هؤلاء
    -0.91
    θρώ
    -0.89
    ódź
    -0.88
     ļ
    -0.87
    ऩ
    -0.86
    POSITIVE LOGITS
    țele
    0.99
     ciudadana
    0.97
     dinyatakan
    0.97
     ocultar
    0.97
    explanatory
    0.95
    шено
    0.94
    ţele
    0.93
     berfungsi
    0.92
    accine
    0.92
     analizar
    0.91
    Activations Density 0.000%

    No Known Activations