© 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-16K
    7. 1257
    Prev
    Next
    INDEX
    Explanations

    next or same

    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_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
    ли
    1.37
    де
    1.26
    муще
    1.19
     охорони
    1.13
    민국
    1.10
     eTo
    1.08
     whereupon
    1.07
    <unused368>
    1.07
     adanya
    1.06
     вся
    1.06
    POSITIVE LOGITS
    p
    1.63
    ために
    1.34
    ki
    1.33
     thriller
    1.31
    م
    1.27
    etten
    1.26
     nedenle
    1.25
    یل
    1.23
    am
    1.22
    b
    1.22
    Activations Density 0.285%

    No Known Activations