© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24867
    Prev
    Next
    INDEX
    Explanations

    mine, minefield, mining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    uyễn
    0.45
     представить
    0.40
     राजू
    0.38
     பச்சை
    0.38
    pxy
    0.38
    itans
    0.38
     नपु
    0.37
    形成的
    0.37
    akai
    0.37
    ଃ
    0.36
    POSITIVE LOGITS
     mine
    0.77
     Mine
    0.71
    Mine
    0.68
    mine
    0.58
     mining
    0.54
    MINE
    0.52
     mined
    0.52
     mines
    0.51
     shaft
    0.49
     mina
    0.49
    Activations Density 0.003%

    No Known Activations