© 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. 22-GEMMASCOPE-RES-131K
    7. 33637
    Prev
    Next
    INDEX
    Explanations

    programming class identifiers

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

    The neuron is triggered by class‐inheritance patterns—i.e. superclass or base‐class names in import statements and “extends”/“class” 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
     and
    -1.36
     or
    -1.00
     Variable
    -0.91
     gdyby
    -0.87
     wybrać
    -0.85
    だったり
    -0.85
     lebte
    -0.81
    になったら
    -0.80
    ристання
    -0.79
    chapter
    -0.79
    POSITIVE LOGITS
     redor
    0.93
    éis
    0.92
     recomendable
    0.91
     desconocido
    0.91
     炒め
    0.91
     inaugura
    0.90
     caricatura
    0.89
     sembler
    0.88
     intérprete
    0.88
     Chbosky
    0.87
    Activations Density 0.014%

    No Known Activations