© 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. 34-GEMMASCOPE-RES-131K
    7. 59468
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    The neuron is a “natural‐language detector” that fires strongly on English words in prose, comments, license texts, or ads rather than on code tokens.

    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
    Fy
    -0.77
    吸
    -0.72
    zionalità
    -0.69
    러스트
    -0.68
    回去
    -0.66
    tad
    -0.66
    roblast
    -0.66
     Mackenzie
    -0.65
    thon
    -0.65
     Kristin
    -0.65
    POSITIVE LOGITS
    лением
    0.73
     coupable
    0.68
     الكبير
    0.67
     HEPA
    0.67
    rels
    0.67
    mucha
    0.66
    umbe
    0.66
     lata
    0.64
    ives
    0.64
     película
    0.64
    Activations Density 0.092%

    No Known Activations