© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11804
    Prev
    Next
    INDEX
    Explanations

    SVM classification

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

    references to Support Vector Machines (SVM) in technical or programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron strongly activates on occurrences of the acronym “SVM” (in any context, e.g. “svm”, “SVM”, “LIBSVM”), so it is detecting mentions of support‐vector‐machine.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ↵
    -4.44
     =
    -2.84
    2
    -2.58
    1
    -2.25
     —
    -2.23
     ;
    -2.23
    );
    -2.17
     {
    -2.17
     �
    -2.16
     eer
    -2.14
    POSITIVE LOGITS
     télécharge
    2.16
    얏
    2.05
    eſt
    2.05
     OBIT
    2.02
     网络
    2.02
    塒
    1.94
    鯔
    1.94
    醅
    1.92
    耵
    1.91
    ᛬
    1.88
    Activations Density 0.001%

    No Known Activations