© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36324
    Prev
    Next
    INDEX
    Explanations

    initials and expansions

    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
     this
    -1.56
     by
    -1.48
    Istorija
    -1.23
     one
    -1.18
     it
    -1.18
    мяг
    -1.17
     ткани
    -1.16
     not
    -1.15
     for
    -1.13
     which
    -1.13
    POSITIVE LOGITS
     who
    2.47
    mbgg
    1.26
     dueño
    1.25
     srdce
    1.21
    tská
    1.20
    primarily
    1.19
    ish
    1.18
    numericUpDown
    1.14
    especially
    1.13
    useNewUrlParser
    1.13
    Activations Density 0.026%

    No Known Activations