© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42246
    Prev
    Next
    INDEX
    Explanations

    Smart + noun

    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
    ↵
    -4.41
     praktisch
    -3.08
     dando
    -2.64
    皛
    -2.59
     technisch
    -2.58
     AMAZING
    -2.58
     
    -2.58
     Jeśli
    -2.50
     shimmering
    -2.48
    ské
    -2.44
    POSITIVE LOGITS
    In
    3.17
    Some
    3.16
    ،
    3.02
    Even
    3.02
    Here
    2.97
    Like
    2.91
    Since
    2.88
    ة
    2.84
    Most
    2.84
    Many
    2.84
    Activations Density 0.007%

    No Known Activations