© 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. 22-GEMMASCOPE-RES-131K
    7. 15318
    Prev
    Next
    INDEX
    Explanations

    neural network layers and operations

    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
     Ostat
    -1.17
    ′,
    -1.09
     originalmente
    -1.05
    こともあり
    -1.05
     particularmente
    -1.02
    isses
    -1.02
     sekitarnya
    -1.02
    recated
    -0.99
     چگونه
    -0.98
    COO
    -0.95
    POSITIVE LOGITS
     to
    1.59
    Украина
    1.17
     статистики
    1.13
    1.13
     philosophie
    1.13
    IANGLES
    1.12
     CascadeType
    1.06
     noix
    1.04
    1.03
    1.02
    Activations Density 0.004%

    No Known Activations