© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95459
    Prev
    Next
    INDEX
    Explanations

    splitting data randomly

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

    The neuron detects mentions of cross‐validation “folds” (e.g. KFold/StratifiedKFold imports and related fold terminology).

    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
     at
    -1.20
     difficult
    -1.06
     forcing
    -1.02
     possibly
    -1.00
    其他
    -0.99
    BackStack
    -0.98
     receive
    -0.98
    Their
    -0.97
     their
    -0.96
     received
    -0.96
    POSITIVE LOGITS
     échanti
    1.18
    Splits
    1.09
     split
    1.00
    дата
    0.99
    QUÉ
    0.98
     飾り
    0.97
    のうち
    0.95
    AVIS
    0.95
     ABSOL
    0.93
    看一下
    0.93
    Activations Density 0.001%

    No Known Activations