© 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. 1175
    Prev
    Next
    INDEX
    Explanations

    lord, lords, Lord's

    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
    ڧ
    -2.47
    葙
    -2.30
    栳
    -2.27
     églises
    -2.17
     vulgaires
    -2.14
    ."
    -2.13
    nocení
    -2.11
    ꯎ
    -2.09
    lahraga
    -2.06
     daban
    -2.03
    POSITIVE LOGITS
     and
    2.23
     ane
    2.19
    );
    2.17
    <i>
    2.17
    ]
    2.14
     of
    2.13
    你在
    2.11
     You
    2.06
     are
    2.02
    )」
    1.98
    Activations Density 0.010%

    No Known Activations