© 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. 40063
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     in
    -1.34
     after
    -1.34
    توض
    -1.13
     после
    -1.10
    だった
    -1.10
     the
    -1.10
     Kapelle
    -1.09
     Gór
    -1.08
     because
    -1.05
     Gouver
    -1.04
    POSITIVE LOGITS
     experiencias
    1.27
     personer
    1.25
    新しく
    1.22
    檍
    1.21
     verschillende
    1.20
     auténtico
    1.20
    茈
    1.18
    ępnie
    1.15
     boken
    1.15
    ́ng
    1.15
    Activations Density 0.013%

    No Known Activations