© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67955
    Prev
    Next
    INDEX
    Explanations

    #include, control, threads, draft, DAI

    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
     Había
    -0.92
    certain
    -0.88
    tiefel
    -0.85
    強調
    -0.85
    gentes
    -0.85
    ㄀
    -0.85
    ૩
    -0.84
     replaces
    -0.83
     тільки
    -0.83
    通貨
    -0.83
    POSITIVE LOGITS
     broek
    0.85
     jurk
    0.82
    = 
    0.82
    |}{\
    0.81
     børn
    0.79
    kými
    0.79
    ɵɵ
    0.79
    رائه
    0.77
    щено
    0.77
    和大
    0.77
    Activations Density 0.049%

    No Known Activations