© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 4869
    Prev
    Next
    INDEX
    Explanations

    technology, automation, disruption, AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assay
    0.50
     careful
    0.50
     dís
    0.49
     Careful
    0.48
     carefully
    0.47
    飾り
    0.47
     약간
    0.47
    队
    0.46
     decorate
    0.46
     scanty
    0.45
    POSITIVE LOGITS
     tecnologie
    1.07
     teknoloj
    1.04
     technologie
    1.03
     technological
    1.02
     tecnologías
    1.02
     Technologien
    1.01
     tecnologia
    0.97
     tecnologias
    0.97
     technologies
    0.97
     tecnología
    0.96
    Activations Density 0.460%

    No Known Activations