© 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. 34-GEMMASCOPE-RES-131K
    7. 91011
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
     for
    -1.38
    ()
    -1.28
     an
    -1.12
     =>
    -1.12
     so
    -1.09
     from
    -1.09
     all
    -1.09
     on
    -1.09
     this
    -1.05
     by
    -1.04
    POSITIVE LOGITS
    ↵
    1.23
    ...".
    1.05
     nettoyer
    1.04
     местных
    1.04
     BETTER
    1.04
     différents
    1.02
    VERY
    1.02
    ቷ
    1.00
     remplacer
    1.00
    jdzie
    1.00
    Activations Density 0.006%

    No Known Activations