© 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. 6720
    Prev
    Next
    INDEX
    Explanations

    specific tokens and structures

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

    Various possessives and general terms

    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
     ঃ
    0.41
     নেতাকর্ম
    0.39
    ']).
    0.39
     principaux
    0.38
    হইবে
    0.38
     Bevölkerung
    0.38
     প্রভৃতির
    0.37
    ਂ
    0.37
     hlavní
    0.37
     kontrast
    0.36
    POSITIVE LOGITS
     Curb
    0.40
    ________________
    0.39
    *
    0.38
    <h2>
    0.38
    鲛
    0.38
    :::
    0.37
     Guardians
    0.37
        
    0.37
    ières
    0.36
    淥
    0.36
    Activations Density 0.019%

    No Known Activations