© 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. 128706
    Prev
    Next
    INDEX
    Explanations

    programming code parts

    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
     princesa
    -1.20
     guste
    -1.14
     plaît
    -1.13
     nór
    -1.09
     fasse
    -1.09
     kreatif
    -1.08
    よろしくお願いします
    -1.07
     spus
    -1.07
    dekat
    -1.07
    ،
    -1.06
    POSITIVE LOGITS
                                   
    1.14
     Städten
    1.13
     ~
    1.11
     haughty
    1.11
     Эти
    1.09
     ciertos
    1.08
     traffico
    1.05
     aceste
    1.05
     diversos
    1.02
     ciertas
    1.02
    Activations Density 0.039%

    No Known Activations