© 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. 115645
    Prev
    Next
    INDEX
    Explanations

    phone, calls, music, answer

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

    This neuron detects blocks of product specification or technical feature listings (e.g. Bluetooth modules, built-in capabilities, compatibility details) in marketing or instruction text.

    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
     Goodwill
    -0.79
    contributor
    -0.74
     flickering
    -0.73
    羚
    -0.72
    unek
    -0.69
     PSU
    -0.69
     сбора
    -0.68
    ピール
    -0.68
     cuánto
    -0.67
     rect
    -0.66
    POSITIVE LOGITS
     hands
    1.41
     Hands
    1.32
     calls
    1.32
     phone
    1.30
     answer
    1.24
    Answer
    1.16
     music
    1.13
    Hands
    1.11
     Phone
    1.09
     Answer
    1.09
    Activations Density 0.018%

    No Known Activations