© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8368
    Prev
    Next
    INDEX
    Explanations

    mining operations and companies

    np_acts-logits-general · gemini-2.5-flash-lite

    mining and related activities

    np_acts-logits-general · gemini-2.5-flash-lite

    mining

    np_max-act-logits · claude-4-5-sonnet
    Triggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     стрелец
    0.46
    琐
    0.44
    香味
    0.44
    浒
    0.43
    FBSDKApp
    0.42
    眄
    0.41
     buttercream
    0.40
    赝
    0.40
    getVisibility
    0.40
     Caroline
    0.40
    POSITIVE LOGITS
     mining
    2.34
     Mining
    2.14
     miners
    2.11
     miner
    2.06
    Mining
    2.05
    mining
    2.03
    礦
    2.00
     mines
    1.95
    矿
    1.94
     mined
    1.91
    Activations Density 0.463%

    No Known Activations