© 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. 22-GEMMASCOPE-RES-131K
    7. 34918
    Prev
    Next
    INDEX
    Explanations

    file paths and code

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

    The neuron fires on numeric literals (integers and floating-point numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     المل
    -0.92
     measured
    -0.89
     parties
    -0.88
    嘴唇
    -0.86
     depois
    -0.84
     Flächen
    -0.83
     later
    -0.82
    Histology
    -0.81
     único
    -0.81
     vitória
    -0.81
    POSITIVE LOGITS
    hébergement
    0.81
    oskop
    0.79
     дефек
    0.79
    zembro
    0.78
    bzw
    0.77
    ciach
    0.77
    respectively
    0.76
    tiene
    0.76
     스톡
    0.73
    Начало
    0.73
    Activations Density 0.009%

    No Known Activations