© 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. 34-GEMMASCOPE-RES-131K
    7. 64070
    Prev
    Next
    INDEX
    Explanations

    Chinese names and affiliations

    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_34/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
     ulasan
    -0.87
    ブース
    -0.78
    
    -0.77
    Aladdin
    -0.75
    ᗰ
    -0.73
     pemerintahan
    -0.72
     ingrediente
    -0.71
     cabina
    -0.70
    Mej
    -0.68
     perfec
    -0.68
    POSITIVE LOGITS
    Advance
    0.93
    ┇
    0.85
    contained
    0.85
    ∥
    0.84
     señal
    0.84
    ⊥
    0.83
    assword
    0.82
    ω
    0.81
    veda
    0.81
    |}{}
    0.81
    Activations Density 0.013%

    No Known Activations