© 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. 10-GEMMASCOPE-RES-131K
    7. 110595
    Prev
    Next
    INDEX
    Explanations

    words ending in common suffixes

    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_10/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
     but
    -1.50
    putString
    -1.20
     една
    -1.20
    BIÉN
    -1.15
    </strong>
    -1.14
    ліза
    -1.13
     может
    -1.13
     seconde
    -1.13
    isierte
    -1.12
    是因为
    -1.11
    POSITIVE LOGITS
    artifacts
    1.38
    Farbe
    1.38
    Gewicht
    1.29
    Verwendung
    1.25
    ownload
    1.20
    atural
    1.19
    Kapitel
    1.19
     金
    1.18
    多分
    1.17
    тился
    1.17
    Activations Density 0.343%

    No Known Activations