© 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. 39712
    Prev
    Next
    INDEX
    Explanations

    numeric or symbolic prefixes

    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
     to
    -1.48
     when
    -1.27
     for
    -1.26
     at
    -1.18
     which
    -1.17
     then
    -1.04
     before
    -1.02
     sebenar
    -0.93
     another
    -0.92
     this
    -0.90
    POSITIVE LOGITS
    beled
    1.09
     །
    1.03
    ματα
    1.03
    delivered
    0.96
    ὲν
    0.94
     nordrhein
    0.94
    Prerequisites
    0.93
    pendentif
    0.93
     Mathematica
    0.93
     louer
    0.93
    Activations Density 0.001%

    No Known Activations