© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92019
    Prev
    Next
    INDEX
    Explanations

    programming interface definitions

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

    The neuron fires on occurrences of the word “Interface” (in any case) in code, XML, or comments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     verkau
    -1.16
     vorigen
    -1.15
     ubiquitous
    -1.12
    1
    -1.07
    ’;
    -1.05
    ’,
    -1.04
    tries
    -1.01
     foundations
    -1.00
     Stücke
    -1.00
     schwarze
    -0.97
    POSITIVE LOGITS
     Interface
    1.33
     interfaz
    1.32
    {})
    1.31
     utilisateur
    1.27
    interface
    1.25
     brasileño
    1.21
     chileno
    1.19
     INTERFACE
    1.19
    ✍
    1.18
    ')
    1.13
    Activations Density 0.018%

    No Known Activations