© 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. 11827
    Prev
    Next
    INDEX
    Explanations

    benefit and advantage

    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
     शुर
    -1.84
    "});
    -1.76
    sonaro
    -1.76
    </i>
    -1.67
    </th>
    -1.63
    ляция
    -1.61
     encarga
    -1.61
    ництва
    -1.61
    ！」
    -1.60
    ！』
    -1.58
    POSITIVE LOGITS
    fully
    1.90
    櫚
    1.84
    7
    1.76
    These
    1.73
     kilka
    1.70
    饪
    1.70
    2
    1.68
    在他
    1.65
    ？！”
    1.65
    うちの
    1.64
    Activations Density 0.020%

    No Known Activations