© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117033
    Prev
    Next
    INDEX
    Explanations

    string split operations

    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
    унк
    -0.77
     bilden
    -0.75
     altijd
    -0.75
    开的
    -0.72
    GOOGLE
    -0.71
     Beispiel
    -0.71
    ird
    -0.71
     ставить
    -0.69
    caps
    -0.69
     Poli
    -0.69
    POSITIVE LOGITS
    getBytes
    1.01
     costos
    0.85
    Emb
    0.84
    confirmButton
    0.81
     منح
    0.79
     chartered
    0.75
    داشت
    0.75
    zA
    0.74
     комбина
    0.74
     VARCHAR
    0.73
    Activations Density 0.010%

    No Known Activations