© 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. 33022
    Prev
    Next
    INDEX
    Explanations

    introduction to content

    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
     triko
    -1.25
    nende
    -1.09
    BSITE
    -1.09
     ส์
    -1.07
     Kalifor
    -1.07
    Similarly
    -1.07
     capítulo
    -1.07
     ensaio
    -1.06
     keramik
    -1.06
     Kristus
    -1.05
    POSITIVE LOGITS
     and
    1.50
     with
    1.00
     out
    0.92
     it
    0.92
    .
    0.86
     k
    0.79
     all
    0.79
     Projected
    0.77
     net
    0.77
    ,
    0.76
    Activations Density 0.000%

    No Known Activations