© 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. 129317
    Prev
    Next
    INDEX
    Explanations

    source of

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

    This neuron detects mentions of “source” (and its plural) when used to describe something serving as a resource or supply.

    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
    //
    -1.66
    _
    -1.59
    hline
    -1.57
    ed
    -1.43
    めちゃ
    -1.37
    en
    -1.31
     korrekt
    -1.30
    out
    -1.30
     наличии
    -1.29
     heo
    -1.28
    POSITIVE LOGITS
     for
    1.63
    沨
    1.51
     Additionally
    1.44
    řízení
    1.44
     has
    1.41
     is
    1.39
    Crítica
    1.39
    scars
    1.35
    lindung
    1.34
     during
    1.33
    Activations Density 0.151%

    No Known Activations