© 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. 66319
    Prev
    Next
    INDEX
    Explanations

    conjunctions/additions

    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
     sustancias
    -1.06
     acompañado
    -1.05
     erstellt
    -1.05
     '/';
    -1.03
     .,
    -1.03
    alate
    -0.99
     infecciones
    -0.98
     rheinland
    -0.96
    agles
    -0.96
    她和
    -0.95
    POSITIVE LOGITS
     also
    1.91
     نیز
    1.84
     are
    1.67
     भी
    1.63
     ebenfalls
    1.59
     тоже
    1.47
    ก็
    1.38
     também
    1.34
     también
    1.32
     cũng
    1.30
    Activations Density 0.065%

    No Known Activations