© 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. 40068
    Prev
    Next
    INDEX
    Explanations

    function calls and parameters

    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
     then
    -1.12
     one
    -1.07
    また
    -0.98
     одним
    -0.97
     crag
    -0.89
     infile
    -0.89
     iguana
    -0.88
    Spieler
    -0.88
     with
    -0.87
     Komunikasi
    -0.87
    POSITIVE LOGITS
     creativos
    1.08
     is
    1.06
     Preferencias
    0.99
     lámpara
    0.98
     funcionales
    0.94
     enchufe
    0.94
     cargador
    0.94
     tambi
    0.93
     Opiniones
    0.93
     cuya
    0.92
    Activations Density 0.004%

    No Known Activations