© 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. 259
    Prev
    Next
    INDEX
    Explanations

    connecting alternatives with or

    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
    gador
    1.79
    లువ
    1.61
    पंजा
    1.60
    folds
    1.56
    د
    1.56
    ﻈ
    1.53
    сь
    1.51
    gadas
    1.51
    ඤ
    1.51
    ábado
    1.50
    POSITIVE LOGITS
    ণিজ
    1.54
     equivalently
    1.45
    therly
    1.38
     者
    1.33
     risk
    1.33
    wel
    1.29
     پھر
    1.28
    bs
    1.21
    ंत्रिकी
    1.15
    ွာ
    1.14
    Activations Density 0.749%

    No Known Activations