© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 57420
    Prev
    Next
    INDEX
    Explanations

    this time

    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_34/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
    These
    -1.99
     Эти
    -1.62
    这些
    -1.48
    Эти
    -1.41
     takimi
    -1.35
     Estos
    -1.34
    這些
    -1.29
    Ւ
    -1.20
    これらの
    -1.18
    Tomorrow
    -1.16
    POSITIVE LOGITS
     this
    7.81
     diesmal
    4.72
    this
    3.92
    这次
    3.91
     цього
    3.72
     cette
    3.67
    这一次
    3.58
    這次
    3.42
     этой
    3.19
     هذا
    3.05
    Activations Density 0.066%

    No Known Activations