© 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. 22-GEMMASCOPE-RES-131K
    7. 65333
    Prev
    Next
    INDEX
    Explanations

    events will unfold

    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
    Its
    -0.93
    sipasi
    -0.88
    ᵒ
    -0.81
     {?
    -0.80
    了过去
    -0.79
     scaring
    -0.78
     Ceinture
    -0.77
    鎰
    -0.77
     scares
    -0.77
    IsString
    -0.77
    POSITIVE LOGITS
     inevitable
    1.45
     eventually
    1.35
     inevitably
    1.29
     inevit
    1.28
     sooner
    1.23
    inev
    1.17
     finally
    1.05
     Expect
    1.03
     Eventually
    1.02
     predictable
    1.02
    Activations Density 0.045%

    No Known Activations