© 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. 74946
    Prev
    Next
    INDEX
    Explanations

    vector erase operations

    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
    {
    -2.06
    ꜆
    -2.03
    揷
    -1.95
    縯
    -1.87
    别人
    -1.86
    🏢
    -1.86
    }
    -1.85
    蚺
    -1.83
     白い
    -1.82
     dizzy
    -1.77
    POSITIVE LOGITS
    </h3>
    2.66
     Hinsicht
    1.94
     This
    1.87
    おめでとう
    1.85
    )
    1.82
     Еще
    1.79
     Where
    1.76
     pomysł
    1.76
     To
    1.72
    ので
    1.72
    Activations Density 0.016%

    No Known Activations