© 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. 68141
    Prev
    Next
    INDEX
    Explanations

    actual timing or state

    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
     not
    -0.91
     seorang
    -0.82
     so
    -0.77
     InkWell
    -0.75
    Revenir
    -0.73
    대로
    -0.73
    WICH
    -0.71
     nutshell
    -0.71
     three
    -0.70
    mListener
    -0.70
    POSITIVE LOGITS
    實際
    1.47
    実際に
    1.45
    actual
    1.36
    いざ
    1.35
     actual
    1.35
    实际
    1.31
    Actual
    1.27
    到时候
    1.21
     upon
    1.13
    実際
    1.13
    Activations Density 0.077%

    No Known Activations