© 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. 11154
    Prev
    Next
    INDEX
    Explanations

    mathematical and code syntax

    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
     bancos
    -1.33
     cena
    -1.20
    Tú
    -1.17
    umentos
    -1.17
     Nedir
    -1.16
    asinya
    -1.15
    Goku
    -1.14
    ⟵
    -1.13
    Nhan
    -1.12
    ecera
    -1.11
    POSITIVE LOGITS
    However
    1.23
     of
    1.19
    ↵
    1.15
     berdasarkan
    1.11
    <strong>
    1.10
    p
    1.10
     when
    1.09
    Therefore
    1.05
    You
    1.02
    <em>
    1.01
    Activations Density 0.007%

    No Known Activations