© 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-262K
    7. 12351
    Prev
    Next
    INDEX
    Explanations

    discovery and findings

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    л
    4.42
    an
    3.72
    ം
    3.09
    и
    3.07
    сти
    2.93
    ので
    2.83
    า
    2.83
    ০
    2.81
    𝑒
    2.67
    ა
    2.66
    POSITIVE LOGITS
    Οι
    2.96
    nte
    2.76
     Haut
    2.65
    naires
    2.58
    tidak
    2.57
    کھ
    2.55
    她在
    2.55
    忔
    2.54
    nier
    2.53
    s
    2.46
    Activations Density 0.031%

    No Known Activations