© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91707
    Prev
    Next
    INDEX
    Explanations

    a or an

    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_34/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
     такие
    -1.16
     отдельных
    -1.12
     anything
    -1.09
     всичко
    -1.08
    either
    -1.08
     lesquels
    -1.06
     различные
    -1.04
     iemand
    -1.04
    anything
    -1.03
     gdyby
    -1.02
    POSITIVE LOGITS
     a
    4.09
     an
    2.83
     another
    2.33
    的一个
    2.33
     one
    2.16
    一个
    2.16
     एक
    2.13
    了一个
    2.13
     two
    2.00
    一种
    1.98
    Activations Density 0.193%

    No Known Activations