© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10438
    Prev
    Next
    INDEX
    Explanations

    contrast or opposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    非
    0.86
    比
    0.84
    不要
    0.82
     unconventional
    0.81
     غیر
    0.80
     thus
    0.80
     !=
    0.79
    不再
    0.79
     unpaid
    0.78
     нерав
    0.77
    POSITIVE LOGITS
     hingegen
    1.61
     juist
    1.32
     наоборот
    1.23
     dagegen
    1.21
     напротив
    1.11
     comparatively
    1.02
     그렇지
    0.98
     justru
    0.97
    Conversely
    0.96
     మాత్రం
    0.96
    Activations Density 0.153%

    No Known Activations