© 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. 34-GEMMASCOPE-RES-131K
    7. 2770
    Prev
    Next
    INDEX
    Explanations

    progress bar and UI elements

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

    This neuron fires on CamelCase identifiers—especially Android UI/API class and resource names like SeekBar, ProgressBar, onCreate, SavedInstanceState, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    grapher
    -0.72
    每
    -0.72
     उनकी
    -0.70
    OD
    -0.69
    NLS
    -0.69
    FieldDescriptor
    -0.67
    Fermi
    -0.67
     into
    -0.66
     func
    -0.66
    Với
    -0.66
    POSITIVE LOGITS
     progress
    1.88
     Progress
    1.54
    Progress
    1.43
    progress
    1.38
    PROGRESS
    1.34
    setProgress
    1.27
     PROGRESS
    1.27
    进度
    1.20
    progressBar
    1.16
     PB
    1.15
    Activations Density 0.004%

    No Known Activations