© 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. 60444
    Prev
    Next
    INDEX
    Explanations

    triage, quill, Schopenhauer, Bard

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

    The neuron is keyed to multi‐syllable content words carrying distinctive noun-forming or agentive suffixes (–ing, –age, –ard, –our, –al etc.).

    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
     рядом
    -1.89
    e
    -1.82
    на
    -1.82
     verſ
    -1.76
     baumwolle
    -1.75
    ۔
    -1.70
    çou
    -1.67
    〝
    -1.63
    ang
    -1.63
    ate
    -1.63
    POSITIVE LOGITS
    boretum
    2.05
     It
    1.91
     golpea
    1.86
     nemus
    1.84
    ,
    1.82
    囖
    1.76
    姦
    1.73
     意思
    1.73
     resté
    1.72
     These
    1.70
    Activations Density 0.016%

    No Known Activations