© 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. 10-GEMMASCOPE-RES-131K
    7. 102008
    Prev
    Next
    INDEX
    Explanations

    certain [noun]

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

    the word “certain” used as a determiner.

    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
    鵙
    -2.30
    ༷
    -2.22
    {
    -1.99
    Geen
    -1.98
    蚡
    -1.97
    萏
    -1.91
    <
    -1.90
     apparaissent
    -1.89
     payé
    -1.89
     trois
    -1.88
    POSITIVE LOGITS
     specified
    2.30
     specific
    2.16
     amount
    2.06
    大半
    1.97
     assess
    1.95
     designated
    1.93
    ).
    1.92
     increase
    1.91
     —
    1.91
     has
    1.91
    Activations Density 0.012%

    No Known Activations