© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 59033
    Prev
    Next
    INDEX
    Explanations

    rust stripping, paint stripping, blasting

    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_all/layer_41_width_262k_l0_big
    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
    綢
    0.51
     सुगंध
    0.46
     napkins
    0.40
     watery
    0.39
    Waterfall
    0.39
    瀑
    0.39
    Coral
    0.38
     Fishes
    0.37
    தாய
    0.37
    ☂
    0.37
    POSITIVE LOGITS
     stripping
    1.18
     blasting
    1.08
     stripped
    1.03
    stripped
    0.90
     Stri
    0.89
     cleaning
    0.89
     blast
    0.86
     stripper
    0.86
     blasted
    0.84
    Stri
    0.82
    Activations Density 0.004%

    No Known Activations