© 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. 13870
    Prev
    Next
    INDEX
    Explanations

    connecting lists

    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
    になると
    -1.02
    fying
    -1.00
     considera
    -0.98
    ling
    -0.95
    basically
    -0.94
    ériques
    -0.93
    かっこ
    -0.91
     anglès
    -0.91
     origini
    -0.89
    ふわ
    -0.88
    POSITIVE LOGITS
     its
    1.77
    其
    1.13
    Its
    1.10
    فاض
    1.00
    その
    0.96
     within
    0.94
     sparkly
    0.94
     their
    0.93
     which
    0.91
    باح
    0.90
    Activations Density 0.230%

    No Known Activations