© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 91770
    Prev
    Next
    INDEX
    Explanations

    extracting substrings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     smokers
    -0.68
    FileVersion
    -0.68
    cum
    -0.66
    早餐
    -0.66
    ական
    -0.66
    stant
    -0.65
    ial
    -0.65
    Caches
    -0.64
     BMC
    -0.64
    athered
    -0.64
    POSITIVE LOGITS
     substr
    3.13
    substr
    2.89
     substring
    2.83
    substring
    2.73
    Substring
    2.28
    SUB
    1.88
     SUB
    1.86
     sub
    1.84
     Sub
    1.77
    slice
    1.73
    Activations Density 0.027%

    No Known Activations