© 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. 102555
    Prev
    Next
    INDEX
    Explanations

    activation of

    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
    ቼ
    -2.05
    岀
    -2.02
     atau
    -1.96
    heon
    -1.96
     TERR
    -1.89
     方法
    -1.88
    omst
    -1.88
    🥂
    -1.88
     }));
    -1.87
    🌞
    -1.87
    POSITIVE LOGITS
    谖
    2.20
    ↵
    1.87
    ’
    1.80
     Now
    1.78
     Gedanke
    1.78
    瑧
    1.77
    </h6>
    1.76
     ”
    1.75
     bené
    1.75
    ’’
    1.73
    Activations Density 0.407%

    No Known Activations