© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3994
    Prev
    Next
    INDEX
    Explanations

    quantization or precision types

    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_29_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     adjourn
    0.69
     ල
    0.69
    odas
    0.68
    llib
    0.67
     कोले
    0.67
     concurrently
    0.64
     Rendering
    0.63
     lạc
    0.63
     शुभकामना
    0.62
    يله
    0.62
    POSITIVE LOGITS
     quant
    1.33
    quant
    1.25
     Quant
    1.14
    Quant
    1.12
     quantization
    1.02
    量
    1.01
    QUANT
    1.00
     quantification
    0.96
     QUANT
    0.96
     क्वांट
    0.94
    Activations Density 0.196%

    No Known Activations