© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67606
    Prev
    Next
    INDEX
    Explanations

    copyright headers and file beginnings

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

    The neuron is keyed to detect year numbers (4-digit dates) in copyright/license headers.

    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
     bulan
    -1.52
     sué
    -1.49
    ığı
    -1.41
     italiano
    -1.41
     littéraire
    -1.38
     québéco
    -1.38
     anniversaire
    -1.37
    ΜΑ
    -1.32
    arschijnlijk
    -1.32
     моего
    -1.31
    POSITIVE LOGITS
     praticamente
    1.32
    お気軽
    1.29
     it
    1.24
    の中から
    1.21
     considerado
    1.17
     ciddi
    1.17
    ときの
    1.16
     ソー
    1.16
    為に
    1.15
    を変更
    1.15
    Activations Density 0.000%

    No Known Activations