© 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. 38933
    Prev
    Next
    INDEX
    Explanations

    conditional expressions and punctuation

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

    The neuron activates on numeric literals (numbers) in code or query text.

    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
    久し
    -1.23
    わたしは
    -1.23
    łaś
    -1.20
    ごめん
    -1.20
     banderas
    -1.20
    ◯
    -1.16
    我們的
    -1.16
     usamos
    -1.15
    来週
    -1.14
     hés
    -1.12
    POSITIVE LOGITS
    ar
    1.23
    j
    1.13
     jok
    1.09
    valido
    1.09
    se
    1.09
    ki
    1.06
    z
    1.05
    もある
    1.05
    v
    1.02
    rt
    1.01
    Activations Density 0.002%

    No Known Activations