© 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. 86793
    Prev
    Next
    INDEX
    Explanations

    ect, etc, 以及等

    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
     για
    -2.59
    </td>
    -2.38
    ;
    -2.22
     für
    -2.20
     untuk
    -2.19
    欤
    -2.11
    Ꭳ
    -2.09
    痾
    -2.02
     oorsp
    -2.02
     для
    -2.02
    POSITIVE LOGITS
    </strong>
    3.52
    </em>
    3.05
    *
    2.86
    ю
    2.52
     are
    2.47
    </h3>
    2.39
    </h4>
    2.36
    \
    2.25
    /
    2.23
     sebagainya
    2.20
    Activations Density 0.001%

    No Known Activations