© 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. 25609
    Prev
    Next
    INDEX
    Explanations

    code definitions and structures

    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
     those
    -1.19
     there
    -1.04
     even
    -1.03
     Bereichen
    -1.00
     Versammlung
    -0.98
    Šalt
    -0.98
     for
    -0.94
     historischen
    -0.94
     erfolgreichen
    -0.93
     remain
    -0.93
    POSITIVE LOGITS
    卨
    1.39
     confers
    1.13
    cedido
    1.13
    鏷
    1.11
     basi
    1.07
     infrar
    1.03
     despi
    1.01
     sportifs
    1.01
     wees
    1.00
    août
    1.00
    Activations Density 0.005%

    No Known Activations