© 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. 24009
    Prev
    Next
    INDEX
    Explanations

    names and animals

    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
    蘩
    -3.00
     afir
    -2.88
    嵛
    -2.83
     immobili
    -2.73
    咘
    -2.66
     aksesuar
    -2.56
     hermosos
    -2.48
    釙
    -2.34
     ihti
    -2.33
    桄
    -2.31
    POSITIVE LOGITS
    </h1>
    2.94
    ção
    2.80
    He
    2.80
    する
    2.72
    na
    2.70
    The
    2.61
    <i>
    2.59
    <h2>
    2.55
    </i>
    2.53
    an
    2.52
    Activations Density 0.010%

    No Known Activations