© 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. 75086
    Prev
    Next
    INDEX
    Explanations

    database indexes and constraints

    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
    cuits
    -1.13
     transportar
    -1.13
     Hervé
    -1.13
    stunde
    -1.13
    resentação
    -1.12
    縢
    -1.12
    dä
    -1.09
     experiences
    -1.09
    Ꭶ
    -1.07
     müm
    -1.06
    POSITIVE LOGITS
     at
    1.18
     for
    1.10
     on
    1.07
     zusammen
    1.00
    sigma
    1.00
    çada
    1.00
     maggio
    0.98
     کال
    0.96
    Erstellt
    0.96
    Scrollbar
    0.95
    Activations Density 0.035%

    No Known Activations