© 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. 22-GEMMASCOPE-RES-131K
    4. 39768
    Prev
    Next
    INDEX
    Explanations

    in addition to

    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
     this
    -1.52
     each
    -1.46
     itulah
    -1.40
     quite
    -1.38
     berikutnya
    -1.38
     both
    -1.25
     selanjutnya
    -1.24
     głównie
    -1.21
     inilah
    -1.21
     meliputi
    -1.15
    POSITIVE LOGITS
    other
    1.60
    其他
    1.39
     usual
    1.38
     antes
    1.37
    previously
    1.33
    traditional
    1.32
     다른
    1.31
    usual
    1.30
    existing
    1.30
     тради
    1.27
    Activations Density 0.019%

    No Known Activations