© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4453
    Prev
    Next
    INDEX
    Explanations

    devitalized

    np_acts-logits-general · gemini-2.5-flash-lite

    key improvements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    0.41
    日光
    0.38
    镖
    0.38
     Dist
    0.37
     brigades
    0.37
     начи
    0.36
     piped
    0.36
     tubing
    0.36
    卩
    0.35
     Pip
    0.35
    POSITIVE LOGITS
     fissure
    0.54
     cracks
    0.52
     cleft
    0.52
     fissures
    0.46
    Dataset
    0.45
     Sustainability
    0.43
    祝福
    0.43
     sostenibilidad
    0.43
     rift
    0.42
     MD
    0.41
    Activations Density 0.024%

    No Known Activations