© 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. 2859
    Prev
    Next
    INDEX
    Explanations

    maps and reviews

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

    opinions on sensitive public interest topics

    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
     Is
    0.38
    쇠
    0.38
    Զ
    0.38
    ังก
    0.37
    angkan
    0.37
     Engaging
    0.37
    電視
    0.37
    ្ល
    0.37
     Englewood
    0.36
    ()>
    0.36
    POSITIVE LOGITS
    assin
    0.39
    artic
    0.39
    アシ
    0.38
    ball
    0.38
     escapar
    0.37
     authoritative
    0.37
    hosted
    0.37
     نحكي
    0.37
    Bailey
    0.36
    ones
    0.36
    Activations Density 0.000%

    No Known Activations