© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12648
    Prev
    Next
    INDEX
    Explanations

    mining operations and related extraction

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Servlet
    0.52
     curviliné
    0.50
    神经
    0.49
    简洁
    0.46
    香味
    0.46
     Aquarium
    0.45
    侾
    0.45
    Cyt
    0.44
    ുമെന്ന്
    0.44
     buttercream
    0.44
    POSITIVE LOGITS
     mining
    2.50
     Mining
    2.16
    Mining
    2.09
     miners
    2.08
    mining
    2.05
    礦
    2.05
     miner
    2.00
    矿
    1.96
    鉱
    1.93
     mines
    1.91
    Activations Density 0.020%

    No Known Activations