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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68515
    Prev
    Next
    INDEX
    Explanations

    years and dates

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

    The neuron is tuned to pick up on tokens that include apostrophes—i.e. possessive ’s and contractions (like Senna’s or it’s).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Dibrom
    -1.06
    辩
    -1.05
    族館
    -0.97
     Awesome
    -0.91
    なんですね
    -0.91
     возможно
    -0.89
     ljudi
    -0.89
    citation
    -0.88
    },{
    -0.86
    有り
    -0.86
    POSITIVE LOGITS
     جيدة
    1.03
    ورة
    1.01
    それは
    0.96
     masakan
    0.94
     sju
    0.92
     samti
    0.91
     סס
    0.91
     menyen
    0.90
    学生的
    0.90
    durante
    0.89
    Activations Density 0.001%

    No Known Activations