© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58467
    Prev
    Next
    INDEX
    Explanations

    programming, license, unicode

    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_34/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
     Mexicano
    -1.15
     Darío
    -1.07
     Cataluña
    -1.07
     calavera
    -1.07
     Cocina
    -1.06
     Corazón
    -1.02
     castillo
    -1.02
     Templo
    -1.00
     cerveza
    -0.99
     Señora
    -0.97
    POSITIVE LOGITS
    tux
    0.96
    bastian
    0.95
     optimieren
    0.94
     transcendental
    0.90
    ntesis
    0.89
    onViewCreated
    0.88
     tuna
    0.88
    inca
    0.87
     وہ
    0.86
    abuhan
    0.86
    Activations Density 0.011%

    No Known Activations