© 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. 22-GEMMASCOPE-RES-131K
    7. 26005
    Prev
    Next
    INDEX
    Explanations

    function definition parameters

    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_22/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
     when
    -1.36
     if
    -1.25
     your
    -1.13
     you
    -1.09
     this
    -1.07
     even
    -1.03
     its
    -1.00
     do
    -1.00
     You
    -1.00
     which
    -0.98
    POSITIVE LOGITS
     rám
    1.17
    izadores
    1.05
     первым
    1.05
     warszawa
    0.96
     rayons
    0.96
     dát
    0.94
    кипедия
    0.91
     chay
    0.91
     sæ
    0.90
    ického
    0.90
    Activations Density 0.008%

    No Known Activations