© 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. 130944
    Prev
    Next
    INDEX
    Explanations

    code changes cause issues

    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
    länge
    -1.41
    groet
    -1.29
    siyah
    -1.25
     blusa
    -1.25
     komis
    -1.23
    machten
    -1.23
     salonu
    -1.21
    kär
    -1.19
    Cómo
    -1.18
    lampe
    -1.17
    POSITIVE LOGITS
    because
    1.38
     because
    1.36
     will
    1.31
     Although
    1.28
     as
    1.23
     There
    1.23
     Because
    1.22
    C
    1.19
     Some
    1.19
     use
    1.18
    Activations Density 0.007%

    No Known Activations