© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71023
    Prev
    Next
    INDEX
    Explanations

    function parameters and sorting

    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
     akku
    -1.07
    Mijn
    -1.05
     Membre
    -1.05
     菇
    -1.02
     fanta
    -0.96
     persil
    -0.96
    väl
    -0.96
    ของ
    -0.95
     abiye
    -0.93
    婠
    -0.93
    POSITIVE LOGITS
     it
    1.26
     Being
    1.16
     by
    1.11
     costumbres
    1.09
     russischen
    1.08
    It
    1.04
     tuve
    1.03
     беше
    1.02
     малко
    0.99
     (
    0.97
    Activations Density 0.002%

    No Known Activations