© 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. 10-GEMMASCOPE-RES-131K
    7. 66546
    Prev
    Next
    INDEX
    Explanations

    products and services

    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
     there
    -1.91
     or
    -1.84
     или
    -1.59
     یا
    -1.55
     may
    -1.52
     time
    -1.52
     hoặc
    -1.48
     apreciar
    -1.46
    せば
    -1.45
     maybe
    -1.44
    POSITIVE LOGITS
     and
    1.76
    :,,
    1.36
     ۱۱
    1.34
    :|
    1.33
     difp
    1.32
    ☹
    1.31
     obfer
    1.31
     occaf
    1.30
    ,«
    1.26
    -..
    1.26
    Activations Density 0.484%

    No Known Activations