© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2185
    Prev
    Next
    INDEX
    Explanations

    human civilization and condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    lev
    2.52
    с
    2.38
    ings
    2.34
    ilent
    2.32
     ret
    2.32
    clare
    2.27
    OP
    2.26
    Multi
    2.24
    ὼ
    2.22
    angered
    2.18
    POSITIVE LOGITS
    ยนต์
    2.78
    近平
    2.74
    鹂
    2.65
    ্বল
    2.50
    --“
    2.45
    ى
    2.39
    𝐲
    2.38
    𝐝
    2.38
    zey
    2.36
     toBe
    2.36
    Activations Density 0.162%

    No Known Activations