© 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. 17-GEMMASCOPE-2-RES-16K
    7. 13135
    Prev
    Next
    INDEX
    Explanations

    how many, how often, how well

    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_17_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
    ความ
    1.21
    お
    1.09
    çe
    1.08
    お客
    1.06
    uring
    1.06
    щее
    1.05
    ዮ
    1.03
    صل
    1.02
     يح
    1.01
    𝑙
    1.00
    POSITIVE LOGITS
     awesome
    1.39
     immaculate
    1.18
    ди
    1.18
    quela
    1.17
     awful
    1.13
    dys
    1.13
     adjoint
    1.12
     dashing
    1.12
     indignant
    1.12
     intitulé
    1.11
    Activations Density 0.034%

    No Known Activations