© 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. 36013
    Prev
    Next
    INDEX
    Explanations

    after change or comparison

    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
    责编
    -0.91
     eternity
    -0.87
    cidae
    -0.85
    atnya
    -0.82
    arshan
    -0.81
     showcase
    -0.81
     showcased
    -0.81
    haha
    -0.81
     comprends
    -0.80
    tabil
    -0.77
    POSITIVE LOGITS
     after
    1.55
     from
    1.53
     compared
    1.47
     после
    1.40
     після
    1.30
     recently
    1.21
     לאחר
    1.17
     since
    1.10
     than
    1.03
     lately
    1.03
    Activations Density 0.146%

    No Known Activations