© 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-262K
    7. 10880
    Prev
    Next
    INDEX
    Explanations

    level chart

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

    keywords, state, caution, death

    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_262k_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
     bilirubin
    0.41
     pancreas
    0.41
    胰
    0.40
     albumin
    0.39
    蛋白质
    0.39
     pancreatic
    0.38
     vaccinations
    0.37
    图像
    0.36
     microbiome
    0.36
     protein
    0.36
    POSITIVE LOGITS
     جائز
    0.44
    на
    0.43
     बदनाम
    0.42
     запре
    0.41
     предоставляет
    0.41
    🇩
    0.40
    год
    0.39
     rebranded
    0.39
    保有
    0.39
    वली
    0.39
    Activations Density 0.000%

    No Known Activations