© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2926
    Prev
    Next
    INDEX
    Explanations

    false, no, without

    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
    Negative Logits
    хол
    1.23
     GIFs
    1.16
    𝗱
    1.16
     Colleges
    1.15
    🦴
    1.13
     hog
    1.13
     Vapor
    1.11
    𝘥
    1.09
     calyce
    1.09
     puns
    1.08
    POSITIVE LOGITS
    ă
    1.20
    rů
    1.16
    蠻
    1.16
    likely
    1.12
     তাহা
    1.05
    nt
    1.04
    np
    1.02
     мыш
    1.01
     связь
    1.00
     зависимости
    1.00
    Activations Density 0.560%

    No Known Activations