© 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. 10-GEMMASCOPE-RES-131K
    7. 59571
    Prev
    Next
    INDEX
    Explanations

    of the same name

    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_10/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
     even
    -1.93
    鱨
    -1.80
     bahkan
    -1.57
     like
    -1.48
    寕
    -1.44
     where
    -1.41
     дори
    -1.38
    ){$
    -1.37
    
    -1.36
     his
    -1.35
    POSITIVE LOGITS
    銣
    1.60
    h
    1.38
     ANOTHER
    1.38
     Meinung
    1.31
     premed
    1.29
     trams
    1.28
     continuar
    1.25
    дание
    1.24
     dode
    1.21
    feuille
    1.19
    Activations Density 0.017%

    No Known Activations