© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15813
    Prev
    Next
    INDEX
    Explanations

    wood and its properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_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
     পর্
    0.65
     ZnO
    0.63
     metallic
    0.62
     ქ
    0.59
     Greens
    0.59
     тексти
    0.59
    🥬
    0.58
     zirconium
    0.57
     Zhao
    0.57
     گاز
    0.57
    POSITIVE LOGITS
     wood
    2.11
     woodworking
    1.84
     wooden
    1.81
    木
    1.80
     деревя
    1.74
     gỗ
    1.73
     Wood
    1.68
     drewn
    1.67
     timber
    1.65
     kayu
    1.64
    Activations Density 0.183%

    No Known Activations