© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65662
    Prev
    Next
    INDEX
    Explanations

    verify, ascertain, realize, check

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     to
    -2.44
     These
    -2.00
     At
    -1.91
     However
    -1.86
    ]
    -1.84
     If
    -1.80
     When
    -1.73
     esteemed
    -1.70
     During
    -1.67
    <h2>
    -1.65
    POSITIVE LOGITS
     that
    2.09
    这一幕
    1.90
     Ottobre
    1.84
    from
    1.83
    鲧
    1.82
     firsthand
    1.79
     nying
    1.75
     how
    1.73
    取决
    1.69
     vegano
    1.69
    Activations Density 0.012%

    No Known Activations