© 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. 33425
    Prev
    Next
    INDEX
    Explanations

    closing code blocks

    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
     to
    -1.13
    AST
    -1.05
    SUC
    -1.02
    AdvEx
    -1.00
    терапия
    -0.99
    nek
    -0.97
     sei
    -0.94
     cong
    -0.92
    mathrm
    -0.92
     комнату
    -0.92
    POSITIVE LOGITS
     prijzen
    1.24
     devrez
    1.22
     uitvo
    1.16
     llevando
    1.13
     Diſ
    1.13
     jepang
    1.13
     økonom
    1.11
    moss
    1.08
    abund
    1.08
     aanbied
    1.06
    Activations Density 0.006%

    No Known Activations