© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10711
    Prev
    Next
    INDEX
    Explanations

    indicating ideal applicability

    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
    ある
    2.70
    मिटेड
    2.55
    什么是
    2.51
     possibilities
    2.39
    囗
    2.36
    usions
    2.32
    すでに
    2.22
    さまざ
    2.20
     провер
    2.19
    dif
    2.16
    POSITIVE LOGITS
    с
    2.61
    erweise
    2.38
    ἲ
    2.34
    स
    2.29
    ņi
    2.28
    ਵ
    2.20
    bouw
    2.17
    י
    2.14
    𝙮
    2.13
     recor
    2.09
    Activations Density 0.140%

    No Known Activations