© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31329
    Prev
    Next
    INDEX
    Explanations

    string split

    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
     intim
    -0.75
    cmath
    -0.71
     abolition
    -0.71
    DataOutputStream
    -0.70
     widers
    -0.70
    Perl
    -0.69
     протягом
    -0.69
    🐏
    -0.68
    Ѕ
    -0.68
    ReadInt
    -0.67
    POSITIVE LOGITS
     strings
    1.70
     split
    1.55
     string
    1.37
     Strings
    1.30
    String
    1.30
    Strings
    1.27
     String
    1.26
     Split
    1.23
     strs
    1.20
    strings
    1.19
    Activations Density 0.047%

    No Known Activations