© 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-65K
    7. 3528
    Prev
    Next
    INDEX
    Explanations

    climate and science

    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_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
     jeweler
    0.80
    jewelry
    0.79
     déplacer
    0.77
     mię
    0.77
     Jewelry
    0.74
     trink
    0.74
     Jewellery
    0.73
     耐
    0.73
     malleable
    0.72
     bodybuilding
    0.71
    POSITIVE LOGITS
     aerosol
    1.46
     atmospheric
    1.40
     aerosols
    1.39
     climat
    1.34
     tropos
    1.29
     Aeros
    1.22
     Atmospheric
    1.18
     radiative
    1.18
     atmosfé
    1.18
     ocean
    1.17
    Activations Density 0.168%

    No Known Activations