© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111718
    Prev
    Next
    INDEX
    Explanations

    communication channels

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

    the word "channel" or "channels" in marketing, business, and technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron spots mentions of “channel” (especially in marketing or distribution contexts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Also
    -1.82
     eight
    -1.71
    When
    -1.64
     zufolge
    -1.62
    Not
    -1.59
     plethora
    -1.56
    While
    -1.55
    There
    -1.54
    Several
    -1.54
     increases
    -1.52
    POSITIVE LOGITS
     to
    1.70
    蓠
    1.62
    ଃ
    1.58
    莛
    1.54
    茈
    1.46
     acclaimed
    1.45
    |'\
    1.43
     THEM
    1.42
    髫
    1.42
    ፨
    1.41
    Activations Density 0.006%

    No Known Activations