© 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. 67249
    Prev
    Next
    INDEX
    Explanations

    command line arguments

    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
     実例
    -1.58
     排骨
    -1.57
     复古
    -1.52
     saut
    -1.52
     薬局
    -1.52
     estadounid
    -1.52
    鹟
    -1.52
     webb
    -1.51
     広場
    -1.48
     ビキニ
    -1.47
    POSITIVE LOGITS
    T
    1.66
    A
    1.63
    Y
    1.51
    V
    1.45
    L
    1.41
    ed
    1.40
    S
    1.39
    P
    1.38
     A
    1.37
    B
    1.36
    Activations Density 0.044%

    No Known Activations