© 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. 66549
    Prev
    Next
    INDEX
    Explanations

    module imports and declarations

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

    The neuron fires mainly on the names of imported or referenced code entities (e.g. class‐ or type‐style identifiers found in import braces).

    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
    r
    -2.28
    I
    -1.98
    g
    -1.96
     ideen
    -1.92
    s
    -1.87
    美味しく
    -1.68
     hunde
    -1.66
    喾
    -1.66
     Januari
    -1.65
    茹で
    -1.65
    POSITIVE LOGITS
    に興味
    1.94
    の方も
    1.89
    総評
    1.84
    のお話
    1.84
     observado
    1.82
     and
    1.80
    の絵
    1.74
     schwier
    1.73
    に挑戦
    1.72
     \&
    1.71
    Activations Density 0.004%

    No Known Activations