© 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. 28471
    Prev
    Next
    INDEX
    Explanations

    numbered or code lines

    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
     pistolet
    -1.09
     granito
    -1.02
     lavabo
    -1.02
     oeil
    -1.02
     pantalon
    -1.02
    אם
    -1.01
     objet
    -1.01
     miniatura
    -1.00
     guir
    -0.99
     langue
    -0.96
    POSITIVE LOGITS
     Ken
    1.09
     \\
    1.03
     rozmiar
    1.01
     zatem
    0.99
    ropractor
    0.98
     drze
    0.98
     WHEN
    0.95
    ₦
    0.95
    ctor
    0.92
    pulo
    0.92
    Activations Density 0.000%

    No Known Activations