© 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. 10-GEMMASCOPE-RES-131K
    7. 87411
    Prev
    Next
    INDEX
    Explanations

    domain name parts

    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_10/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
     حتى
    -1.05
    也许
    -1.05
     Araújo
    -1.04
     znac
    -1.02
     devices
    -1.02
     helping
    -1.01
    raisers
    -1.01
     s
    -1.01
     maybe
    -1.00
     hasta
    -0.98
    POSITIVE LOGITS
    ğin
    1.15
    pide
    1.14
     ujar
    1.13
    explique
    1.12
     [],
    1.11
     pretože
    1.09
    {},
    1.09
     of
    1.09
    ◆◆
    1.09
    INOIS
    1.08
    Activations Density 1.083%

    No Known Activations