© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10222
    Prev
    Next
    INDEX
    Explanations

    dark + related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_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
    剐
    0.45
    壷
    0.43
     sıcak
    0.39
    Staff
    0.38
    㕵
    0.38
     bipartisan
    0.37
     white
    0.37
    affles
    0.37
     белый
    0.37
    婹
    0.37
    POSITIVE LOGITS
     dark
    1.80
    dark
    1.68
    Dark
    1.68
     Dark
    1.66
     DARK
    1.66
    DARK
    1.59
     darker
    1.58
     darken
    1.44
     darkness
    1.42
     darkest
    1.37
    Activations Density 0.096%

    No Known Activations