© 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. 59921
    Prev
    Next
    INDEX
    Explanations

    contrast or alternative states

    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
     with
    -1.89
    </b>
    -1.87
     These
    -1.82
     आणि
    -1.79
    Expensive
    -1.69
    ꦒ
    -1.67
    诸多
    -1.63
    趼
    -1.63
    などなど
    -1.60
    这件事情
    -1.59
    POSITIVE LOGITS
    The
    2.78
    ್
    1.92
     alemanes
    1.91
    </h3>
    1.90
    。
    1.89
    }
    1.84
    “
    1.84
     {
    1.83
    ☫
    1.82
    ו
    1.80
    Activations Density 0.008%

    No Known Activations