© 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. 84644
    Prev
    Next
    INDEX
    Explanations

    playing fields

    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
    得太
    -1.51
    </h2>
    -1.46
    真正
    -1.45
     фай
    -1.45
    境的
    -1.44
    ви
    -1.41
     strangle
    -1.38
    2
    -1.36
    делы
    -1.34
     shrill
    -1.34
    POSITIVE LOGITS
    </sub>
    1.84
    jenigen
    1.79
    甞
    1.69
    ternos
    1.69
    </h3>
    1.59
    蚡
    1.54
     protegida
    1.53
    ſam
    1.52
    ramid
    1.48
     praktische
    1.48
    Activations Density 0.012%

    No Known Activations