© 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. 8125
    Prev
    Next
    INDEX
    Explanations

    soft focus and lighting

    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
    нт
    0.98
    맑
    0.91
     sampah
    0.89
    었다
    0.88
    städ
    0.86
     hals
    0.85
    ligen
    0.85
    াবার
    0.85
    ビット
    0.85
    মানুষ
    0.85
    POSITIVE LOGITS
     cushion
    1.27
     pliable
    1.25
     cushions
    1.23
     mại
    1.21
     supple
    1.12
    柔
    1.10
     pillow
    1.05
    soft
    1.03
     മൃ
    1.03
     Cushion
    1.01
    Activations Density 0.106%

    No Known Activations