© 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. 8392
    Prev
    Next
    INDEX
    Explanations

    agents or directors

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

    exploit, abuse or endanger

    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
    .​
    0.38
     Sph
    0.37
     흥
    0.37
    曜
    0.36
    ├──
    0.35
    .*;
    0.35
    振
    0.35
     mobs
    0.33
    習
    0.33
     spherical
    0.33
    POSITIVE LOGITS
    ড়ার
    0.44
    ড়া
    0.44
    өз
    0.43
    ড়া
    0.42
     रात्री
    0.40
    钚
    0.40
     roi
    0.39
    য়েক
    0.39
    ')
    0.39
     através
    0.37
    Activations Density 0.063%

    No Known Activations