© 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. 141707
    Prev
    Next
    INDEX
    Explanations

    setup, safe, enable, tire, cards, dens

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

    General intelligence (AGI), variable, data, ratio

    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
     civilization
    0.41
    卢
    0.41
    辈子
    0.41
     registries
    0.40
    一层
    0.39
    ్రహ్
    0.39
    警察
    0.39
    桓
    0.38
     defensa
    0.38
     demanding
    0.38
    POSITIVE LOGITS
    PLAIN
    0.48
     uygun
    0.47
     उत्तरी
    0.47
    ungkin
    0.47
    ynku
    0.46
     ඒ
    0.45
    ছাড়া
    0.45
     बहुतेक
    0.45
    ZA
    0.45
    ባቸው
    0.45
    Activations Density 0.001%

    No Known Activations