© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54291
    Prev
    Next
    INDEX
    Explanations

    programming interfaces

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

    This neuron selectively activates on the occurrence of the token “Interface” (i.e. interface declarations or usages) in code.

    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
     a
    -1.74
     an
    -1.45
     with
    -1.38
     on
    -1.38
     when
    -1.34
     through
    -1.34
     by
    -1.33
     of
    -1.31
     their
    -1.30
     also
    -1.30
    POSITIVE LOGITS
     personnalisés
    1.26
     illustratie
    1.25
     especializados
    1.20
     APPELLANT
    1.19
     necesarios
    1.19
     afbeelding
    1.19
     bienvenida
    1.18
    ᄏ
    1.18
    voorbeeld
    1.13
     VOOR
    1.13
    Activations Density 0.010%

    No Known Activations