© 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. 41-GEMMASCOPE-2-RES-262K
    7. 8954
    Prev
    Next
    INDEX
    Explanations

    border styles and properties

    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
    ]/*
    0.49
     yeast
    0.49
     pivots
    0.47
     hemodynamic
    0.47
     fermentation
    0.46
     manžel
    0.46
     suami
    0.46
     reasonableness
    0.45
     økonom
    0.45
     centroids
    0.45
    POSITIVE LOGITS
     border
    0.96
    border
    0.93
    얇
    0.92
    Border
    0.91
     Border
    0.89
     thin
    0.89
    Solid
    0.88
     Thickness
    0.88
    thin
    0.86
    Thin
    0.85
    Activations Density 0.007%

    No Known Activations