© 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. 2619
    Prev
    Next
    INDEX
    Explanations

    tools and their applications

    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
    ра
    2.83
    𝘦
    2.80
    𝘪
    2.74
    𝘱
    2.68
     involution
    2.52
    𝚘
    2.51
    ˏ
    2.51
    𝘢
    2.50
    ?=
    2.48
    ʳ
    2.48
    POSITIVE LOGITS
     bantu
    3.34
    м
    2.98
    ية
    2.82
    ومن
    2.71
     Fakat
    2.69
     torno
    2.60
    tips
    2.41
    та
    2.38
    kits
    2.35
     sores
    2.35
    Activations Density 0.142%

    No Known Activations