© 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. 95586
    Prev
    Next
    INDEX
    Explanations

    table view cells and list items

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

    The neuron activates on Android UI–related code identifiers and imports (e.g. class names like “Cells,” “LinearLayout,” “Gravity,” and android.widget/ android.content imports).

    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
     elizabeth
    -1.02
     virginia
    -0.97
    quina
    -0.93
    odeon
    -0.93
     thofe
    -0.93
     to
    -0.92
    DrawerToggle
    -0.92
    볼
    -0.91
    alanta
    -0.91
     heron
    -0.90
    POSITIVE LOGITS
     doble
    1.21
     where
    1.20
     crafted
    1.14
     này
    1.11
     with
    1.09
    ariConfig
    1.07
     felicitación
    1.05
     vueltas
    1.02
     huella
    1.02
     cará
    1.02
    Activations Density 0.012%

    No Known Activations