© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8027
    Prev
    Next
    INDEX
    Explanations

    paper sizes

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

    image aspect ratio and dimensions

    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
     oon
    0.39
     volat
    0.38
     volatil
    0.38
     antipode
    0.37
     esti
    0.37
     substantiated
    0.37
     sculpt
    0.36
    }\,
    0.36
    particles
    0.36
     hesit
    0.36
    POSITIVE LOGITS
     sheets
    1.02
     शीट
    0.98
     sheet
    0.92
     Landscape
    0.91
     Letter
    0.90
    sheets
    0.89
    Landscape
    0.89
     DIN
    0.88
     landscape
    0.88
     postcard
    0.88
    Activations Density 0.107%

    No Known Activations