© 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. 8010
    Prev
    Next
    INDEX
    Explanations

    fill in or out

    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
    ার
    1.40
     Diffraction
    1.29
    ouilles
    1.21
     composés
    1.19
    ೆಂಟ್
    1.16
    y
    1.14
    াৰ
    1.14
    
    1.13
     صارف
    1.13
    𝗰
    1.13
    POSITIVE LOGITS
     gaps
    1.42
     gap
    1.26
     coffers
    1.22
    填
    1.19
     Fill
    1.18
     voids
    1.12
    Voids
    1.12
    Filling
    1.11
     dold
    1.09
     filled
    1.08
    Activations Density 0.039%

    No Known Activations