© 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. 22-GEMMASCOPE-2-RES-262K
    7. 5906
    Prev
    Next
    INDEX
    Explanations

    aid deliveries are

    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
    Negative Logits
     ten
    0.64
     master
    0.62
     over
    0.62
     second
    0.59
     enough
    0.58
     nothing
    0.57
     added
    0.57
     word
    0.56
    /
    0.56
     became
    0.55
    POSITIVE LOGITS
     площадь
    0.82
    積分
    0.81
    ontiti
    0.80
    ประสิทธิภาพ
    0.80
    ktCap
    0.79
    fdPar
    0.79
    收聽
    0.78
     fecund
    0.77
    散热
    0.77
     ganancias
    0.76
    Activations Density 0.001%

    No Known Activations