© 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. 9-GEMMASCOPE-2-RES-16K
    7. 1482
    Prev
    Next
    INDEX
    Explanations

    plant growth and planting material

    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_9_width_16k_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
    س
    2.98
    ور
    2.74
    er
    2.72
     thermique
    2.70
     hará
    2.69
    ుల
    2.59
    ుడు
    2.58
    ול
    2.53
    ب
    2.51
    erler
    2.48
    POSITIVE LOGITS
    পালা
    3.45
    ય
    2.59
     skepticism
    2.56
    ,\,\
    2.48
    ગી
    2.44
     INCRE
    2.39
    可以选择
    2.37
    "%
    2.34
    ִי
    2.34
     uptake
    2.32
    Activations Density 0.372%

    No Known Activations