Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7285
    Prev
    Next
    INDEX
    Explanations

    implementing actions

    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_9_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
    ☞
    2.51
    ਰ
    2.24
     overw
    2.24
    是在
    2.20
    দের
    2.19
     équip
    2.18
    식
    2.17
    лки
    2.14
     gaw
    2.13
    ThreadPool
    2.12
    POSITIVE LOGITS
    ead
    2.23
    ൺ
    2.17
    is
    2.16
    عاد
    2.16
    ig
    2.11
    ем
    2.09
    غ
    2.08
    ль
    2.04
    ار
    2.01
    tad
    1.98
    Activations Density 0.075%

    No Known Activations