© 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. 60981
    Prev
    Next
    INDEX
    Explanations

    news agency abbreviations

    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
     rhein
    -1.29
     also
    -1.28
    뺀
    -1.27
     ندار
    -1.24
    ácii
    -1.23
     capace
    -1.19
     arduous
    -1.18
    ialmente
    -1.18
    蒔
    -1.18
    сение
    -1.16
    POSITIVE LOGITS
    paar
    1.28
    ዜ
    1.16
     매우
    1.16
    Föld
    1.16
     repeats
    1.13
    >
    1.13
     čist
    1.13
    之际
    1.13
    gunaan
    1.12
    着的
    1.11
    Activations Density 0.007%

    No Known Activations