© 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. 10-GEMMASCOPE-RES-131K
    7. 69118
    Prev
    Next
    INDEX
    Explanations

    recent times and future dates

    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_10/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
     eier
    -1.43
     nimmer
    -1.42
     simpel
    -1.42
     eisen
    -1.39
     spion
    -1.39
     harte
    -1.34
     Dansk
    -1.32
     was
    -1.32
     damen
    -1.30
    /**
    -1.30
    POSITIVE LOGITS
    Even
    1.51
    为什么会
    1.41
     calentamiento
    1.38
    Since
    1.35
     Verhältnis
    1.34
    他們的
    1.34
    Because
    1.33
    even
    1.33
    Usually
    1.32
    優雅
    1.32
    Activations Density 0.087%

    No Known Activations