© 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. 618
    Prev
    Next
    INDEX
    Explanations

    counting numbers in lists

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

    sorting and searching algorithms

    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
    <unused95>
    0.44
     भवन
    0.44
     учре
    0.43
    Appellant
    0.43
    豪华
    0.43
    嬅
    0.43
    私募基金
    0.42
    殡
    0.42
    พระ
    0.41
    律师
    0.41
    POSITIVE LOGITS
     list
    0.54
     sorted
    0.54
     count
    0.53
     find
    0.52
     sorting
    0.51
     ArrayList
    0.50
     consecutive
    0.50
    找出
    0.49
     sum
    0.48
     largest
    0.48
    Activations Density 0.004%

    No Known Activations