© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71476
    Prev
    Next
    INDEX
    Explanations

    delivery and production timeframes

    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
     his
    -1.20
     already
    -1.17
    derry
    -1.04
    AsStream
    -0.98
    一大
    -0.94
    ýš
    -0.93
     sítio
    -0.93
    髂
    -0.92
     CEST
    -0.92
     Betrachtung
    -0.91
    POSITIVE LOGITS
    depending
    1.26
     بعد
    1.23
     brengen
    1.20
     wachten
    1.20
     after
    1.17
     depending
    1.13
     éto
    1.12
     minimum
    1.10
    bánh
    1.10
    cche
    1.09
    Activations Density 0.011%

    No Known Activations