© 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. 34-GEMMASCOPE-RES-131K
    7. 31577
    Prev
    Next
    INDEX
    Explanations

    legal filings and abbreviations

    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
     undoubtedly
    -1.87
     all
    -1.84
     there
    -1.84
     gives
    -1.77
     first
    -1.70
     definitely
    -1.69
     began
    -1.68
     undeniably
    -1.67
     one
    -1.66
     although
    -1.66
    POSITIVE LOGITS
     ,'
    1.84
    !!!!!!!
    1.84
    為に
    1.73
     Dinas
    1.71
     !!!!!
    1.66
     trône
    1.66
     vrijdag
    1.64
    めっちゃ
    1.63
    !!!!!!
    1.59
     ij
    1.57
    Activations Density 0.206%

    No Known Activations