© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60778
    Prev
    Next
    INDEX
    Explanations

    so followed by a descriptor

    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
    "",
    -2.00
     from
    -1.92
     to
    -1.89
    8
    -1.85
     through
    -1.77
    0
    -1.77
     after
    -1.76
     is
    -1.76
    赑
    -1.74
     多少
    -1.70
    POSITIVE LOGITS
    <bos>
    1.98
    蓠
    1.76
    </h1>
    1.72
     precisamente
    1.61
    ма
    1.61
     ス
    1.61
    ⑤
    1.56
    鱇
    1.55
    ‍
    1.54
     
    1.53
    Activations Density 0.013%

    No Known Activations