© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99245
    Prev
    Next
    INDEX
    Explanations

    Apple ecosystem support

    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
     Lieu
    -0.79
     depositing
    -0.73
    ourdes
    -0.72
     edifício
    -0.71
     谷
    -0.71
    orak
    -0.69
     overcrow
    -0.68
    numRows
    -0.68
    degenerative
    -0.67
    valido
    -0.66
    POSITIVE LOGITS
    Spoljašnje
    0.87
     menambah
    0.79
    bogen
    0.79
     Apple
    0.76
    zegovina
    0.76
    lias
    0.75
    チコミ
    0.75
    Apple
    0.75
     المؤلف
    0.75
    KJV
    0.75
    Activations Density 0.037%

    No Known Activations