© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1281
    Prev
    Next
    INDEX
    Explanations

    words ending in -ing or -ize

    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_29_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
    ᄆ
    0.85
    础
    0.82
    ņas
    0.80
    itiva
    0.77
    icional
    0.77
     എടു
    0.75
     setSearch
    0.73
    悱
    0.72
     Remover
    0.72
    ونکي
    0.71
    POSITIVE LOGITS
    izing
    1.25
    izzando
    1.17
    ifferentiating
    1.13
    stituting
    1.12
    ifying
    1.08
    uating
    1.07
    itating
    1.06
    izando
    1.05
    ulating
    1.05
    ifferentiate
    1.02
    Activations Density 0.619%

    No Known Activations