© 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. 14449
    Prev
    Next
    INDEX
    Explanations

    cultural immersion

    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
    nd
    1.82
    ﻕ
    1.68
     সমঝো
    1.65
    ﺵ
    1.61
     बाजू
    1.56
    ﺭ
    1.51
    Rooms
    1.48
     поступ
    1.47
    janje
    1.46
     ok
    1.45
    POSITIVE LOGITS
    ⊂
    2.14
    tooltip
    2.11
     sugary
    2.07
    wark
    2.01
    stitial
    2.00
    ⣀
    1.99
     カラー
    1.98
     wetland
    1.97
     talisman
    1.96
    гно
    1.95
    Activations Density 0.000%

    No Known Activations