© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57099
    Prev
    Next
    INDEX
    Explanations

    this followed by noun

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

    The neuron activates on adjectives or adverbs that signal relative chronology or versioning—e.g. “new,” “newly,” “newer,” “same,” “old.”

    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
    だいたい
    -1.02
     místo
    -0.99
     disait
    -0.99
    うわ
    -0.98
    从来
    -0.93
     erfre
    -0.92
    YECTO
    -0.92
     perfeito
    -0.92
    あー
    -0.90
     voyez
    -0.89
    POSITIVE LOGITS
     SOON
    1.06
    ですので
    1.02
    子が
    1.00
    蝌
    0.92
    สินค้า
    0.91
    巴掌
    0.91
     muss
    0.89
    ٖ
    0.89
    yelidikan
    0.88
     kanssa
    0.87
    Activations Density 0.574%

    No Known Activations