© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 37583
    Prev
    Next
    INDEX
    Explanations

    before bedbefore cookingbefore closingbefore bedtime

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    1.17
    al
    1.13
    r
    1.11
    m
    1.10
    ل
    1.07
    ج
    1.07
    ین
    1.05
    n
    1.04
    ut
    1.02
    b
    1.00
    POSITIVE LOGITS
     übrigens
    1.13
     justices
    1.10
     paneles
    1.10
     appréci
    1.07
     capazes
    1.06
     fabricantes
    1.05
     indispensables
    1.05
     harán
    1.05
     dangere
    1.04
     startActivity
    1.03
    Activations Density 0.009%

    No Known Activations