© 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. 29-GEMMASCOPE-2-RES-262K
    7. 146143
    Prev
    Next
    INDEX
    Explanations

    drinking water

    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
    Not in Any Lists

    No Comments

    Negative Logits
    लेटर
    0.70
     وار
    0.69
    アリ
    0.68
     Hyd
    0.68
    贷
    0.67
    Editors
    0.65
    лари
    0.64
    טל
    0.64
    simx
    0.64
     Vegetation
    0.64
    POSITIVE LOGITS
     supply
    0.82
     straw
    0.79
     очки
    0.74
    용
    0.73
    сона
    0.73
     fuente
    0.73
     Supply
    0.73
     fuentes
    0.72
     जलाने
    0.72
     troughs
    0.72
    Activations Density 0.001%

    No Known Activations