© 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. 36230
    Prev
    Next
    INDEX
    Explanations

    crafting wooden tools and 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
    Not in Any Lists

    No Comments

    Negative Logits
     ब्लॉक
    0.46
     灯
    0.41
     блоков
    0.41
    块
    0.41
     playable
    0.40
     Upload
    0.40
     бю
    0.40
     blocs
    0.40
    Uploaded
    0.40
     glazed
    0.40
    POSITIVE LOGITS
     mining
    0.51
     Mining
    0.46
    Mining
    0.45
     récol
    0.44
     Barbara
    0.43
     Joan
    0.42
    斧
    0.42
     requirements
    0.41
     chopping
    0.41
     tools
    0.40
    Activations Density 0.010%

    No Known Activations