© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 3212
    Prev
    Next
    INDEX
    Explanations

    breakdown of categories

    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_17_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
     or
    1.35
     или
    1.30
     atau
    1.29
     లేదా
    1.24
     किंवा
    1.21
     або
    1.20
    或
    1.18
     ឬ
    1.18
     یا
    1.13
     أو
    1.10
    POSITIVE LOGITS
    ên
    1.28
    ست
    1.15
    ol
    1.13
     Subsequently
    1.13
    te
    1.08
    el
    1.05
    as
    1.05
    ёл
    1.02
    льним
    1.02
    itäten
    1.01
    Activations Density 0.113%

    No Known Activations