© 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. 20419
    Prev
    Next
    INDEX
    Explanations

    sequence of definition

    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
    -
    -1.74
     other
    -1.70
    ?
    -1.66
     from
    -1.52
     on
    -1.48
    b
    -1.43
     which
    -1.42
      
    -1.39
     or
    -1.35
    .
    -1.34
    POSITIVE LOGITS
     joyería
    1.63
     Garantía
    1.55
     personalización
    1.53
     casado
    1.52
     Gestión
    1.51
     alkoholu
    1.50
     Consejos
    1.50
    ߜ
    1.44
     ilustración
    1.39
     tranquilidad
    1.39
    Activations Density 0.081%

    No Known Activations