© 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. 10-GEMMASCOPE-RES-131K
    4. 18991
    Prev
    Next
    INDEX
    Explanations

    Producers Releasing Corporation

    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
    ův
    -1.35
    ränken
    -1.24
    είται
    -1.22
     where
    -1.20
    \$
    -1.20
    strasse
    -1.18
     harten
    -1.16
    straße
    -1.16
     návště
    -1.16
    ță
    -1.14
    POSITIVE LOGITS
     kinds
    1.39
     protects
    1.38
    慙
    1.36
     diverso
    1.34
    Boas
    1.32
     می‌توانید
    1.31
    достатки
    1.29
     cherished
    1.27
     treasured
    1.27
    ۰
    1.26
    Activations Density 0.096%

    No Known Activations