© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35211
    Prev
    Next
    INDEX
    Explanations

    android ui components

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

    The neuron fires on mentions of Android UI libraries, components, and related XML/Java package or attribute names.

    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
    🦳
    -1.40
    
    -1.27
     دیجیتال
    -1.23
     високо
    -1.21
     gustado
    -1.16
     feroit
    -1.16
     our
    -1.15
     them
    -1.13
     HERBERT
    -1.11
    ']='
    -1.09
    POSITIVE LOGITS
    <bos>
    1.20
    ांकि
    1.06
    чают
    1.05
     =-\
    1.05
    ilitatea
    1.01
    rshire
    1.00
    förmig
    1.00
    Твор
    1.00
     Karnataka
    1.00
    Kepala
    0.98
    Activations Density 0.003%

    No Known Activations