© 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. 77295
    Prev
    Next
    INDEX
    Explanations

    class Phonebook Person

    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
     N
    -0.85
     unusually
    -0.83
     m
    -0.83
     multi
    -0.83
     on
    -0.82
     אנ
    -0.80
     fun
    -0.79
     stating
    -0.77
     also
    -0.76
     out
    -0.75
    POSITIVE LOGITS
    XmlAccessorType
    0.93
     personagens
    0.92
     MOON
    0.91
     camiset
    0.90
     TIT
    0.90
     Schauspielerin
    0.90
     publie
    0.89
     Clues
    0.88
    Ȓ
    0.87
    癭
    0.87
    Activations Density 0.008%

    No Known Activations