© 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. 101299
    Prev
    Next
    INDEX
    Explanations

    billionaire and wealth

    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
     fairytale
    -2.56
     manchmal
    -2.14
    </b>
    -2.14
    骨折
    -2.09
    ↵↵
    -2.05
    ኡ
    -2.03
     駅前
    -2.02
    𝕫
    -1.99
     besonderen
    -1.98
     schwier
    -1.97
    POSITIVE LOGITS
    ’，
    2.39
    ,"
    2.39
    鼱
    2.39
    </h3>
    2.14
    嚒
    2.11
     involves
    2.05
    ti
    2.05
    "
    2.03
    蟊
    2.00
    阋
    1.99
    Activations Density 0.005%

    No Known Activations