© 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. 22-GEMMASCOPE-2-RES-262K
    7. 11378
    Prev
    Next
    INDEX
    Explanations

    asking for clarification details

    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
    ה
    1.57
    a
    1.55
    在
    1.49
    en
    1.26
    an
    1.25
    er
    1.21
    ার
    1.12
    -
    1.12
    ة
    1.10
    ه
    1.02
    POSITIVE LOGITS
     Darüber
    1.54
     Specifically
    1.48
     Namely
    1.46
     Besides
    1.43
     Particularly
    1.41
     Especially
    1.39
     Özellikle
    1.39
     That
    1.38
     Atau
    1.37
     Además
    1.32
    Activations Density 0.109%

    No Known Activations