© 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. 127309
    Prev
    Next
    INDEX
    Explanations

    machine learning classification algorithms

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

    The neuron fires strongly on technical machine-learning terminology—especially names of algorithms (e.g. SVM, logistic regression, kernel ridge) and related hyperparameter terms (e.g. C, gamma, cross-validation, grid search).

    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
     navegar
    -1.28
     vidro
    -1.27
     angen
    -1.27
    рили
    -1.27
     which
    -1.27
     Preferencias
    -1.27
    骉
    -1.23
    dering
    -1.22
     roues
    -1.22
    mec
    -1.21
    POSITIVE LOGITS
    STALK
    1.17
    謁
    1.13
     könnten
    1.12
     U
    1.09
    DEVELOP
    1.09
     kommen
    1.07
    ртуаль
    1.05
    ]
    1.05
    tonsoft
    1.05
     Set
    1.05
    Activations Density 0.052%

    No Known Activations