© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14187
    Prev
    Next
    INDEX
    Explanations

    words ending in ing or of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     giết
    1.42
    zei
    1.36
     stomp
    1.36
     डेब्यू
    1.35
    赎
    1.34
    吼
    1.34
     谢
    1.32
     wipe
    1.31
     애니
    1.31
    sthresh
    1.30
    POSITIVE LOGITS
    <blockquote>
    1.14
    物が
    1.10
    पर
    1.05
    企業の
    1.05
    ทำการ
    1.04
     actividades
    1.03
    ⽇
    1.02
     Mineral
    1.02
     कारकों
    1.02
    Mineral
    1.00
    Activations Density 0.562%

    No Known Activations