© 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. 95814
    Prev
    Next
    INDEX
    Explanations

    programming imports database modules

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

    The neuron fires on occurrences of “db” in code import or module paths (e.g. django.db, android.database).

    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
    隳
    -1.25
    Ꮴ
    -1.23
     dėl
    -1.21
     harte
    -1.20
    春天
    -1.20
     donnera
    -1.17
     atacante
    -1.17
    afbeelding
    -1.17
    DÉ
    -1.16
     manifeste
    -1.14
    POSITIVE LOGITS
    <bos>
    1.52
    دى
    1.11
    TRIBUN
    1.10
    lankton
    1.10
    з
    1.05
    靄
    1.02
    槤
    1.02
     welchen
    1.02
    游戏亮点
    1.02
     oxígeno
    1.00
    Activations Density 0.000%

    No Known Activations