© 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. 22-GEMMASCOPE-2-RES-65K
    7. 8248
    Prev
    Next
    INDEX
    Explanations

    where can

    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_65k_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
    𝐢
    1.44
    𝐞
    1.30
    ために
    1.29
    𝐚
    1.27
    𝐝
    1.11
    ａ
    1.11
    রি
    1.10
    𝐭
    1.06
    ENT
    1.06
    tos
    1.03
    POSITIVE LOGITS
    abouts
    1.47
    fore
    1.35
     учета
    1.34
    ን
    1.33
     родился
    1.33
     pää
    1.22
    ן
    1.19
    ঙালি
    1.13
    队
    1.11
    다
    1.11
    Activations Density 0.023%

    No Known Activations