© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 19804
    Prev
    Next
    INDEX
    Explanations

    website for

    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_22_width_262k_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
     permettant
    0.92
     destiné
    0.91
    讓
    0.82
     permettre
    0.80
    让
    0.78
     используется
    0.78
     umożliw
    0.78
     использоваться
    0.77
     otomatis
    0.76
     Dzięki
    0.76
    POSITIVE LOGITS
     for
    1.36
    for
    1.11
     учун
    0.89
     für
    0.87
     untuk
    0.87
     للح
    0.86
    សម្រាប់ការ
    0.84
     pentru
    0.83
     для
    0.82
     ([
    0.82
    Activations Density 0.037%

    No Known Activations