© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128109
    Prev
    Next
    INDEX
    Explanations

    lists starting with "Portable"

    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
    ֢
    -1.18
     Qualquer
    -1.10
    ſelves
    -1.07
     资源
    -1.06
     Ainda
    -1.03
     TÉCNICA
    -1.02
    噜
    -1.01
     Porém
    -1.01
     застосування
    -0.99
     向量
    -0.96
    POSITIVE LOGITS
    ’
    1.29
    </blockquote>
    1.09
    –
    1.05
    within
    1.02
    2
    1.02
     –
    0.97
    ↵↵↵↵↵↵↵
    0.95
    .’
    0.95
    ↵
    0.94
    </tr>
    0.94
    Activations Density 0.000%

    No Known Activations