© 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. 45580
    Prev
    Next
    INDEX
    Explanations

    mobile technology usage

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

    The neuron fires on ordinary running text (natural‐language sentences) but remains off in code snippets, URLs, or other non-prose segments.

    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
     Kinect
    -1.11
     Cagliari
    -0.92
     AudioClip
    -0.89
    iPad
    -0.83
     Ebola
    -0.81
     Skype
    -0.81
     skype
    -0.77
     компью
    -0.77
     Retina
    -0.77
    beli
    -0.77
    POSITIVE LOGITS
     androidx
    1.26
     Realme
    1.20
     Samsung
    1.09
     OnePlus
    1.09
    OnePlus
    1.08
     realme
    1.02
     Oreo
    0.99
     Google
    0.99
     Redmi
    0.98
     Huawei
    0.96
    Activations Density 0.031%

    No Known Activations