© 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. 128560
    Prev
    Next
    INDEX
    Explanations

    code comments 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
    ἵ
    -1.29
     recursos
    -1.27
    ﻷ
    -1.15
     Objetivos
    -1.14
     دیکھیے
    -1.13
     Sekarang
    -1.13
    wegg
    -1.12
     Pastikan
    -1.12
     quindi
    -1.11
     więc
    -1.11
    POSITIVE LOGITS
     befand
    1.13
    キロ
    1.13
    ष्य
    1.07
     épices
    1.05
    Parfait
    1.04
    chränk
    1.03
     suscripción
    1.02
     médicaments
    1.02
    当时的
    1.02
     aliments
    1.02
    Activations Density 0.001%

    No Known Activations