© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11722
    Prev
    Next
    INDEX
    Explanations

    language versions and mixed sources

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

    evaluate answer or threat

    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_31_width_16k_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
    Carlos
    0.47
    गुड
    0.45
    ركه
    0.45
    子
    0.44
    زر
    0.44
    ゥ
    0.43
    覷
    0.43
    脤
    0.42
    use
    0.42
    రువు
    0.42
    POSITIVE LOGITS
     farther
    0.55
     graduates
    0.54
     iskust
    0.47
     aspirants
    0.47
     الاعداد
    0.47
     experience
    0.46
     মাধ্যমিক
    0.46
     تجربه
    0.45
    ²
    0.45
     magazine
    0.45
    Activations Density 0.007%

    No Known Activations