© 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. 105147
    Prev
    Next
    INDEX
    Explanations

    the [proper noun/noun]

    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
     -
    -1.67
     těch
    -1.53
     aleación
    -1.51
    };*/
    -1.46
     (
    -1.41
     umož
    -1.40
     FEBR
    -1.39
    ...)
    -1.38
    )",
    -1.37
    ...")
    -1.36
    POSITIVE LOGITS
     of
    2.16
     можно
    1.80
     {},
    
    1.69
    ⊺
    1.69
     This
    1.65
     fünf
    1.57
    ,
    
    1.55
     这
    1.51
     viejas
    1.51
    を
    1.49
    Activations Density 0.057%

    No Known Activations