© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 13202
    Prev
    Next
    INDEX
    Explanations

    underground digging

    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_12_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
    ale
    0.94
    ーク
    0.93
     segit
    0.92
    عرض
    0.90
     โม
    0.88
    alen
    0.88
     entourage
    0.86
    </strong>
    0.85
     язы
    0.85
    вью
    0.85
    POSITIVE LOGITS
     tunnelling
    1.38
     tunnels
    1.34
     tunneling
    1.30
     Underground
    1.26
     subterr
    1.23
    地下
    1.22
     Groundwater
    1.19
     subterranean
    1.16
     excavations
    1.15
     खुदाई
    1.13
    Activations Density 0.153%

    No Known Activations