© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60600
    Prev
    Next
    INDEX
    Explanations

    proximity alert

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

    This neuron detects Android resource density qualifiers (e.g. ldpi, mdpi, hdpi, dpi).

    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
    ographers
    -0.85
     larger
    -0.73
    傳
    -0.73
     Վեր
    -0.71
     Wię
    -0.71
     бать
    -0.71
    umably
    -0.71
    BitConverter
    -0.70
     Przed
    -0.70
     Pathway
    -0.70
    POSITIVE LOGITS
     pixels
    0.90
    Geschäfts
    0.84
    DEN
    0.83
    ειν
    0.81
    美味しいです
    0.80
     Lacto
    0.79
    یلی
    0.79
    sowie
    0.78
    huset
    0.78
     Governors
    0.78
    Activations Density 0.001%

    No Known Activations