© 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-262K
    7. 145629
    Prev
    Next
    INDEX
    Explanations

    physical attributes

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     estilo
    0.89
     ben
    0.87
    PopupButton
    0.87
    ben
    0.86
     стиля
    0.82
     stylu
    0.81
    㭋
    0.81
    Ben
    0.80
     七
    0.80
    <unused207>
    0.80
    POSITIVE LOGITS
     physical
    4.70
     Physical
    4.62
    Physical
    4.53
    physical
    4.27
     PHYSICAL
    3.93
     physically
    3.46
     физи
    3.40
    物理
    3.26
     physicality
    3.22
     фізи
    3.22
    Activations Density 0.006%

    No Known Activations