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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7549
    Prev
    Next
    INDEX
    Explanations

    finding by id

    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
    ة
    2.45
    ه
    2.38
    𝐁
    2.18
    이
    2.09
     mathbf
    2.03
    هي
    1.96
    संख्या
    1.93
    ర్చు
    1.90
    𝐒
    1.88
     tf
    1.88
    POSITIVE LOGITS
    াসে
    1.77
     próximo
    1.53
    ieurs
    1.52
    р
    1.51
     yönelik
    1.48
     invigorating
    1.48
    teenth
    1.46
     abode
    1.45
     узнать
    1.45
     grü
    1.44
    Activations Density 0.000%

    No Known Activations