© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102497
    Prev
    Next
    INDEX
    Explanations

    implements interface declarations

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

    the keyword "implements" in programming code, indicating class or interface implementation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron fires on tokens in type‐declaration lines where a class/struct/protocol name is declaring conformance or implementation of an interface (e.g. the “implements” keyword or its language‐specific equivalent).

    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
     their
    -1.85
     упаковке
    -1.63
     usai
    -1.63
     设备
    -1.54
     incroy
    -1.49
     voler
    -1.49
     音乐
    -1.48
    齷
    -1.48
     作り方
    -1.48
    ’,
    -1.46
    POSITIVE LOGITS
    "--
    1.60
    ")
    1.56
    ="
    1.48
    詭
    1.47
     巷
    1.47
     creator
    1.43
    </u>
    1.42
     fría
    1.40
    ↵↵
    1.39
    pantalones
    1.38
    Activations Density 0.012%

    No Known Activations