© 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. 34-GEMMASCOPE-RES-131K
    4. 65435
    Prev
    Next
    INDEX
    Explanations

    signal strength and battery status

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

    The neuron fires on network- and telecom-related technical acronyms and identifiers (e.g. WiFi, SSID, MAC, signal, periodicity).

    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
    زا
    -0.76
    AnchorStyles
    -0.75
    )++;
    -0.74
     Browns
    -0.74
     asiático
    -0.71
     parlamentar
    -0.71
    DMETHOD
    -0.69
    sinh
    -0.69
    osp
    -0.68
    حق
    -0.68
    POSITIVE LOGITS
     signal
    1.93
     strength
    1.69
     level
    1.56
     battery
    1.52
     levels
    1.52
    signal
    1.45
    Signal
    1.41
    strength
    1.41
     bars
    1.38
     Signal
    1.37
    Activations Density 0.019%

    No Known Activations