© 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. 10-GEMMASCOPE-RES-131K
    7. 13134
    Prev
    Next
    INDEX
    Explanations

    proper names followed by last names

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

    The neuron is firing on code‐style opening parentheses (the “(” token) in these Django migration snippets.

    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
    -2.06
    8
    -1.60
    After
    -1.59
    9
    -1.53
    5
    -1.51
    Despite
    -1.49
     ''
    -1.47
    Unlike
    -1.47
    Each
    -1.40
    "
    -1.39
    POSITIVE LOGITS
     they
    2.77
    桄
    1.63
     dalších
    1.55
    鈊
    1.47
     overarching
    1.41
    Metallic
    1.39
     wiedzy
    1.39
     verschillende
    1.38
    
    1.35
     działal
    1.34
    Activations Density 0.001%

    No Known Activations