© 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. 11028
    Prev
    Next
    INDEX
    Explanations

    code imports and declarations

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

    This neuron detects fully qualified package or module path segments in import (or package) declarations.

    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
     but
    -1.17
     permitirá
    -1.17
    Seems
    -1.15
    ᵛ
    -1.13
     limpar
    -1.13
     realizan
    -1.08
     horrifying
    -1.05
    普通人
    -1.05
     muitos
    -1.04
     insanely
    -1.04
    POSITIVE LOGITS
     even
    1.36
     Even
    1.26
     so
    1.20
     also
    1.18
    Even
    1.17
    ;
    1.10
     kuhusu
    1.02
    [];
    1.02
     ndani
    1.01
     there
    1.00
    Activations Density 0.020%

    No Known Activations