© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99323
    Prev
    Next
    INDEX
    Explanations

    configuration, code, settings

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

    The neuron fires on programming‐language import/include statements—especially Java “import” lines and the package/class names that follow.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     começou
    -1.50
    MatIconModule
    -1.27
    مرحله
    -1.27
     في
    -1.24
     perdeu
    -1.23
     ไม่
    -1.19
     ersten
    -1.19
    JpaRepository
    -1.18
    </h1>
    -1.17
     devido
    -1.16
    POSITIVE LOGITS
     for
    1.74
     that
    1.23
     your
    1.17
     about
    1.16
     now
    1.16
    room
    1.13
     thereupon
    1.13
     you
    1.13
     subsequently
    1.09
     this
    1.09
    Activations Density 0.194%

    No Known Activations