© 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. 59434
    Prev
    Next
    INDEX
    Explanations

    references to current or previous work

    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
     again
    -1.38
     for
    -1.24
     when
    -1.22
    やはり
    -1.20
    觐
    -1.05
     nuevamente
    -1.02
     from
    -1.02
     just
    -1.01
     botines
    -0.99
     выборе
    -0.97
    POSITIVE LOGITS
     this
    2.66
    previous
    2.06
     previous
    1.99
     Previous
    1.87
    Previous
    1.87
     هذا
    1.80
    This
    1.77
     본
    1.77
     herein
    1.73
     This
    1.70
    Activations Density 0.538%

    No Known Activations