© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65831
    Prev
    Next
    INDEX
    Explanations

    processing and results

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

    The neuron is picking out Chinese verbs that describe key actions or results (e.g. 可以, 得到, 发现, 使用, 改变).

    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
    0
    -1.80
    。”
    -1.78
    4
    -1.74
     mengucap
    -1.70
     ventajas
    -1.63
    1
    -1.59
    3
    -1.58
     diferencias
    -1.55
    hmigung
    -1.52
    8
    -1.52
    POSITIVE LOGITS
     and
    2.05
     to
    1.77
     when
    1.56
     until
    1.55
     decipher
    1.45
     where
    1.39
    )
    1.36
    饜
    1.34
    しば
    1.34
     tonight
    1.34
    Activations Density 0.006%

    No Known Activations