© 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. 67662
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and symbols

    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
     ワイド
    -1.02
    ädchen
    -1.00
     PLACE
    -0.99
    stepping
    -0.93
     serisi
    -0.93
     They
    -0.93
    ighted
    -0.93
     简约
    -0.91
     AMERICAN
    -0.90
     notícia
    -0.90
    POSITIVE LOGITS
     +
    1.60
     =
    1.39
     →
    1.29
     ==
    1.23
     ->
    1.19
     >>
    1.12
    ⇆
    1.05
     =>
    1.03
     -->
    0.99
    ＝
    0.98
    Activations Density 0.097%

    No Known Activations