© 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. 851
    Prev
    Next
    INDEX
    Explanations

    technologies, alterations, equipment, strategies

    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
     because
    -1.88
    貰
    -1.56
     pequeñas
    -1.50
    isuus
    -1.48
    Sejarah
    -1.44
     německ
    -1.44
    Berdasarkan
    -1.41
    Én
    -1.39
    肄
    -1.36
    因為
    -1.35
    POSITIVE LOGITS
     APPELLANT
    1.48
    alties
    1.30
     rejet
    1.30
     UserService
    1.26
    ᾽
    1.24
     conftest
    1.23
     cerveza
    1.22
    tilizer
    1.22
     fatale
    1.20
     pulumi
    1.19
    Activations Density 0.448%

    No Known Activations