© 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. 22-GEMMASCOPE-RES-131K
    7. 25610
    Prev
    Next
    INDEX
    Explanations

    programming code constructs

    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_22/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
    に行ってきました
    -1.16
     recensement
    -1.11
     всегда
    -1.11
     Grecs
    -1.07
     они
    -1.07
     gött
    -1.01
    に行きました
    -1.01
     Jeśli
    -1.00
    ണം
    -0.99
     Theologie
    -0.99
    POSITIVE LOGITS
     maar
    1.24
    了几
    1.16
    /**/
    1.10
     rasch
    1.09
    那样
    1.09
     diciembre
    1.09
     XV
    1.08
    瞟
    1.07
    嘅
    1.04
    [][
    1.03
    Activations Density 0.023%

    No Known Activations