© 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. 93057
    Prev
    Next
    INDEX
    Explanations

    python file encoding declarations

    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
    drip
    -0.75
     Vietnam
    -0.73
     diversos
    -0.72
    れていた
    -0.72
     bedeutend
    -0.70
    厅
    -0.70
    ës
    -0.70
    >("
    -0.70
     Brunswick
    -0.69
     $>$
    -0.69
    POSITIVE LOGITS
     coding
    2.03
     -*-
    2.00
    coding
    1.66
     encoding
    1.33
    encoding
    1.22
    #!/
    1.17
    Coding
    1.17
     codific
    1.03
    #!
    1.00
     Coding
    0.99
    Activations Density 0.113%

    No Known Activations