© 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. 10-GEMMASCOPE-RES-131K
    7. 112701
    Prev
    Next
    INDEX
    Explanations

    variable y

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

    The neuron fires on instances of the variable “y” (especially in contexts like y_pred, y_true, y_<number>, etc.).

    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
    al
    -3.25
    émoc
    -2.86
    ężczy
    -2.81
    ünste
    -2.50
    riezmann
    -2.48
     своем
    -2.47
     марта
    -2.42
    ↵
    -2.42
    禤
    -2.41
    軔
    -2.41
    POSITIVE LOGITS
    1
    3.27
    "
    2.75
    在他的
    2.58
    9
    2.47
    0
    2.42
    7
    2.34
    +
    2.31
    8
    2.30
    
    2.25
    老闆
    2.20
    Activations Density 0.035%

    No Known Activations