© 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. 24-GEMMASCOPE-2-RES-262K
    7. 3625
    Prev
    Next
    INDEX
    Explanations

    contrast and negation

    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_24_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
    ,
    0.68
    ),
    0.54
    )
    0.48
    (
    0.48
    ()
    0.47
    .
    0.47
    -
    0.45
    "",
    0.45
    :
    0.45
    (),
    0.44
    POSITIVE LOGITS
     choć
    0.62
     אבל
    0.61
     protože
    0.57
     albeit
    0.56
     aunque
    0.55
     però
    0.55
     তবে
    0.52
     क्योंकि
    0.51
     Folks
    0.51
     mutta
    0.51
    Activations Density 0.059%

    No Known Activations