© 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. 72392
    Prev
    Next
    INDEX
    Explanations

    converting input into output

    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
    外部連結
    -1.13
     grupper
    -1.06
    っていますが
    -1.05
    认同
    -1.01
     държа
    -1.00
    进行了
    -0.99
     arbejds
    -0.98
     CERTAIN
    -0.96
    消失了
    -0.96
    りましたが
    -0.96
    POSITIVE LOGITS
     a
    1.43
     into
    1.24
     actually
    1.09
     marchio
    1.08
     something
    1.05
    fauteuil
    1.05
     which
    1.05
     Versuche
    1.03
     his
    1.02
     nyata
    1.02
    Activations Density 0.049%

    No Known Activations