© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3894
    Prev
    Next
    INDEX
    Explanations

    abstract noun suffixes: -ism, -ist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     καρ
    0.55
    ्रो
    0.55
     regardless
    0.54
     statuses
    0.54
    OVER
    0.52
    चान
    0.52
     ασ
    0.51
     [[
    0.51
    ળા
    0.51
     दशा
    0.50
    POSITIVE LOGITS
    ist
    2.53
    istic
    2.21
    ism
    2.08
    ists
    2.06
    主义
    1.96
    istische
    1.94
    IST
    1.94
    ismo
    1.88
    istisch
    1.83
    ista
    1.81
    Activations Density 0.160%

    No Known Activations