© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 896
    Prev
    Next
    INDEX
    Explanations

    executing steps or instructions

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

    code execution results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    疹
    0.52
    OLYBDENUM
    0.48
    넬
    0.47
    Methyl
    0.47
    鸬
    0.47
    柺
    0.46
    篾
    0.46
    挎
    0.46
     ఊ
    0.46
     శరీర
    0.46
    POSITIVE LOGITS
     try
    0.63
     execute
    0.61
     perform
    0.60
     apply
    0.57
     applying
    0.56
     result
    0.55
     build
    0.55
     start
    0.53
     invoke
    0.53
     call
    0.52
    Activations Density 0.001%

    No Known Activations