© 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. 73692
    Prev
    Next
    INDEX
    Explanations

    Jared Allen, Valentine

    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
    に来て
    -1.17
     provides
    -1.14
     data
    -1.09
     
    -1.06
     radiador
    -1.06
    ḻ
    -1.05
     mantuvo
    -1.04
     empieza
    -1.03
     Dě
    -1.03
     important
    -1.02
    POSITIVE LOGITS
    ponses
    1.28
    ounid
    1.27
    istible
    1.19
     durer
    1.17
    躥
    1.13
     oeil
    1.12
     vanden
    1.11
     agir
    1.10
     celles
    1.09
     assister
    1.08
    Activations Density 0.001%

    No Known Activations