© 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. 65438
    Prev
    Next
    INDEX
    Explanations

    on-site services and offerings

    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
    </b>
    -2.17
    </h5>
    -2.02
    𓋼
    -1.93
    </td>
    -1.80
     behulp
    -1.79
    牁
    -1.77
    ”،
    -1.73
    牆
    -1.72
     häufiger
    -1.71
    ukkah
    -1.70
    POSITIVE LOGITS
     incluso
    1.80
    瞜
    1.79
    的很
    1.77
    最重要
    1.74
    同伴
    1.73
     masih
    1.71
    posia
    1.68
     deterioro
    1.65
     ambition
    1.64
     recomenda
    1.63
    Activations Density 0.006%

    No Known Activations