© 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. 129044
    Prev
    Next
    INDEX
    Explanations

    artillery, Ortiz, arthritis

    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
    黽
    -2.77
    泺
    -2.77
     شیپور
    -2.66
    琹
    -2.42
    栊
    -2.41
    ⦊
    -2.41
    sandalia
    -2.39
    苤
    -2.38
     یا
    -2.36
    镦
    -2.36
    POSITIVE LOGITS
    }
    3.08
     That
    2.84
    mathrm
    2.75
     
    2.72
     Hinblick
    2.72
    </strong>
    2.61
    {
    2.58
    );
    2.56
    )-
    2.56
     to
    2.50
    Activations Density 0.007%

    No Known Activations