© 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. 2201
    Prev
    Next
    INDEX
    Explanations

    communication channel or pathway

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

    This neuron activates on occurrences of the word “channel” (in any context or casing).

    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
     conquista
    -1.37
     ferrovia
    -1.32
     croce
    -1.23
     crescente
    -1.22
     palestra
    -1.20
     tutela
    -1.19
     biografia
    -1.17
     psicologia
    -1.15
     censura
    -1.13
     promessa
    -1.13
    POSITIVE LOGITS
     Channel
    1.55
     chan
    1.53
    led
    1.52
    channel
    1.40
    chan
    1.40
     CH
    1.38
     Ch
    1.37
    getChannel
    1.27
     channe
    1.23
     channeling
    1.21
    Activations Density 0.018%

    No Known Activations