© 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. 34-GEMMASCOPE-RES-131K
    7. 64201
    Prev
    Next
    INDEX
    Explanations

    end date markers

    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
    during
    -1.00
    uol
    -0.90
     MILES
    -0.88
    路
    -0.88
    🍆
    -0.88
     principali
    -0.86
    mega
    -0.86
    bó
    -0.85
     durante
    -0.85
     yetu
    -0.85
    POSITIVE LOGITS
     time
    1.74
     earliest
    1.45
     now
    1.34
     period
    1.32
     today
    1.16
     times
    1.14
     when
    1.13
     date
    1.05
     periods
    1.05
    šanas
    1.02
    Activations Density 0.011%

    No Known Activations