© 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. 72569
    Prev
    Next
    INDEX
    Explanations

    code snippets and file names

    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
     mój
    -1.20
     veículos
    -1.18
     honlap
    -1.13
     farmacé
    -1.10
    containing
    -1.09
     allerede
    -1.09
     apoio
    -1.09
     actualización
    -1.08
    rosos
    -1.07
     automó
    -1.06
    POSITIVE LOGITS
     first
    1.55
     one
    1.31
    1
    1.23
    !
    1.08
     d
    1.07
    d
    1.06
     R
    1.04
     D
    1.02
     foglie
    1.00
    を行います
    0.99
    Activations Density 0.001%

    No Known Activations