© 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. 13671
    Prev
    Next
    INDEX
    Explanations

    code directives and identifiers

    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
     their
    -1.73
     you
    -1.65
     most
    -1.46
     only
    -1.34
     both
    -1.33
     two
    -1.29
     your
    -1.28
     an
    -1.20
     second
    -1.20
     my
    -1.18
    POSITIVE LOGITS
     새로운
    1.30
     لهذه
    1.29
    といった
    1.25
    なども
    1.24
     mangled
    1.23
     禁止
    1.20
    Cerca
    1.20
     Эти
    1.20
     aprobó
    1.20
    井上
    1.19
    Activations Density 0.008%

    No Known Activations