© 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. 4448
    Prev
    Next
    INDEX
    Explanations

    active states or voter ID

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

    active engagement

    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
    舶
    0.38
     Takahashi
    0.36
    برى
    0.35
    眥
    0.35
     delicios
    0.34
    ijkl
    0.34
    eppo
    0.33
    쭐
    0.33
    ለሁ
    0.33
    ंत्र
    0.32
    POSITIVE LOGITS
     active
    5.16
     Active
    4.88
     актив
    4.78
    active
    4.75
     ACTIVE
    4.72
    Active
    4.69
     aktif
    4.56
    ACTIVE
    4.34
     activo
    4.22
     aktive
    4.19
    Activations Density 0.376%

    No Known Activations