© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11968
    Prev
    Next
    INDEX
    Explanations

    Miranda Kerr or documentation tags

    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_10/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
    verture
    -2.05
    tivazione
    -1.87
     ТАК
    -1.84
     JOSÉ
    -1.82
    illir
    -1.82
     ПОД
    -1.80
    mbito
    -1.80
     zove
    -1.77
    ceton
    -1.76
     Thereafter
    -1.70
    POSITIVE LOGITS
     is
    2.48
     "
    2.08
     the
    2.05
    \\
    1.92
     a
    1.91
     it
    1.77
     two
    1.71
     something
    1.66
     
    1.64
     respekt
    1.63
    Activations Density 0.003%

    No Known Activations