© 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. 128092
    Prev
    Next
    INDEX
    Explanations

    code, error, or documentation constructs

    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
     also
    -1.12
    :
    -1.09
    ,
    -1.03
    师兄
    -0.89
    companyname
    -0.89
    totalPage
    -0.88
    会い
    -0.86
    -
    -0.84
    守り
    -0.84
     prepare
    -0.84
    POSITIVE LOGITS
     millioner
    1.12
    signee
    1.10
    nyata
    1.08
    lactin
    1.08
    CLUD
    1.08
     eeuw
    1.06
    
    1.06
    strcmp
    1.05
    了口气
    1.05
    =$?
    1.05
    Activations Density 0.034%

    No Known Activations