© 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. 66415
    Prev
    Next
    INDEX
    Explanations

    object.property access

    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
     vín
    -1.30
    要点
    -1.25
     potra
    -1.24
     Mulher
    -1.20
    dây
    -1.20
    spectos
    -1.20
    六年
    -1.16
    Pratique
    -1.16
     Saúde
    -1.16
    Sudah
    -1.16
    POSITIVE LOGITS
     indivíduos
    1.37
     byen
    1.34
     regeringen
    1.32
     weißem
    1.27
     perioden
    1.25
     },
    1.17
     ``
    1.16
     soportes
    1.16
     gobiernos
    1.16
    țiunea
    1.16
    Activations Density 0.003%

    No Known Activations