© 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. 11587
    Prev
    Next
    INDEX
    Explanations

    ok or yeah or haha followed by comma

    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
     to
    -1.59
     myös
    -1.56
     incluso
    -1.55
    erende
    -1.52
     sogar
    -1.50
     in
    -1.45
    Ayrıca
    -1.44
    美元
    -1.41
     休閒
    -1.39
     anche
    -1.38
    POSITIVE LOGITS
     zouden
    1.50
     they
    1.48
     are
    1.44
    1
    1.41
     where
    1.41
     didn
    1.37
     did
    1.37
     can
    1.33
    ,
    1.33
    的道
    1.32
    Activations Density 0.029%

    No Known Activations