© 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. 118287
    Prev
    Next
    INDEX
    Explanations

    linear television distribution

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

    The neuron strongly responds to tokens naming TV‐ and streaming‐industry concepts (e.g. “streaming,” “network,” “platform,” “rights,” “cable,” “subscription”).

    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
    Бележки
    -0.77
     Garry
    -0.74
     siento
    -0.74
     Helen
    -0.74
    余裕
    -0.70
    currentState
    -0.69
    ahora
    -0.68
     sensu
    -0.68
    又能
    -0.68
     Welt
    -0.67
    POSITIVE LOGITS
     linear
    1.84
    Linear
    1.65
    linear
    1.63
    LINEAR
    1.50
     LINEAR
    1.41
     Linear
    1.40
    线性
    1.23
     distribution
    1.21
     lineal
    1.16
     liné
    1.10
    Activations Density 0.063%

    No Known Activations