© 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. 36045
    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_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
     and
    -1.59
     who
    -1.32
     will
    -1.21
     birçok
    -1.16
     the
    -1.13
     {};
    -1.10
     there
    -1.10
     memberikan
    -1.08
     Fällen
    -1.07
    ↵↵
    -1.05
    POSITIVE LOGITS
     maksi
    1.36
     aktiviteter
    1.31
     anniversaire
    1.31
     nytt
    1.28
     milj
    1.27
     vulga
    1.25
     tatou
    1.25
     kuu
    1.24
     produkter
    1.20
     murale
    1.20
    Activations Density 0.030%

    No Known Activations