© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 3144
    Prev
    Next
    INDEX
    Explanations

    reported by news media

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

    media outlets and online platforms

    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
     持
    0.46
     subdivided
    0.41
    ண்முக
    0.40
     Jurisdiction
    0.39
    ⊥
    0.38
     =)
    0.38
     Absence
    0.37
    廻
    0.36
    compressible
    0.36
     jurisdic
    0.36
    POSITIVE LOGITS
     Huffington
    1.79
     Reuters
    1.77
     CNN
    1.76
     Daily
    1.62
     CNBC
    1.61
     BBC
    1.59
    CNN
    1.58
    Reuters
    1.58
     newspaper
    1.55
     Corriere
    1.54
    Activations Density 0.413%

    No Known Activations