© 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. 22-GEMMASCOPE-RES-131K
    7. 27544
    Prev
    Next
    INDEX
    Explanations

    New findings, Q:, Welcome to

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

    The neuron flags occurrences of programming‐language library or module references (e.g. import/include lines naming standard packages like java.util or C++ 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
     壁纸
    -1.04
     to
    -0.96
     開催
    -0.95
     дуже
    -0.92
     техні
    -0.90
    벚
    -0.90
     bijou
    -0.90
     AMEN
    -0.89
    рования
    -0.89
     betalen
    -0.89
    POSITIVE LOGITS
     डॉ
    0.99
    めんなさい
    0.98
    H
    0.96
     ребенку
    0.92
    んでる
    0.92
     zwykle
    0.92
    che
    0.90
    hu
    0.90
     are
    0.89
    Tra
    0.89
    Activations Density 0.006%

    No Known Activations