© 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. 15242
    Prev
    Next
    INDEX
    Explanations

    android adapter classes

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

    The neuron detects occurrences of adapter‐related code (e.g. instantiating or assigning an Adapter and calling setAdapter).

    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
    bringt
    -1.10
     sandalias
    -1.08
     individualism
    -1.01
     Septiembre
    -1.00
     impresionante
    -0.99
    iaj
    -0.95
    mij
    -0.94
     caixas
    -0.94
     impresionantes
    -0.93
     Imágenes
    -0.93
    POSITIVE LOGITS
     egenskaper
    1.06
    ⟞
    1.03
    하려
    1.02
     يقوم
    0.98
    minated
    0.98
    vač
    0.98
    ura
    0.97
     ませ
    0.95
    鿬
    0.94
     cellulite
    0.94
    Activations Density 0.003%

    No Known Activations