© 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. 44045
    Prev
    Next
    INDEX
    Explanations

    reasonable price

    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
    edere
    -1.66
    ichert
    -1.59
    aning
    -1.55
    ICIENCY
    -1.54
     başlad
    -1.50
     gezet
    -1.48
    
    -1.47
     doigts
    -1.46
    zzet
    -1.46
     campeones
    -1.45
    POSITIVE LOGITS
        
    1.50
     has
    1.48
    {~
    1.43
     if
    1.39
    ",
    1.39
     currently
    1.28
    abá
    1.27
     can
    1.26
     still
    1.22
    ).
    1.21
    Activations Density 0.035%

    No Known Activations