© 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. 5491
    Prev
    Next
    INDEX
    Explanations

    giving thanks

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

    unwanted pornography

    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
     বাদ
    0.40
    rome
    0.39
     pl
    0.38
     finishing
    0.38
    flash
    0.37
    javax
    0.36
    v
    0.36
    astien
    0.36
     sledge
    0.36
     straw
    0.35
    POSITIVE LOGITS
    嶙
    0.42
     आराम
    0.40
    गरण
    0.39
     დ
    0.38
    伤
    0.38
     menswear
    0.38
     المرا
    0.38
    屹
    0.38
    铆
    0.38
     Overs
    0.37
    Activations Density 0.007%

    No Known Activations