© 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. 10-GEMMASCOPE-RES-131K
    7. 74531
    Prev
    Next
    INDEX
    Explanations

    Madame, Hoover, Laguna

    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
    然后
    -2.77
     größer
    -2.36
    ,[
    -2.36
    replyreport
    -2.31
    antaranya
    -2.25
    
    -2.25
     religiosas
    -2.22
     preciosas
    -2.19
     contado
    -2.19
    阐
    -2.17
    POSITIVE LOGITS
     \
    2.97
    }$
    2.95
    i
    2.81
    ſſen
    2.78
    <em>
    2.78
    amp
    2.69
    as
    2.56
    most
    2.50
     när
    2.41
    ꦢ
    2.38
    Activations Density 0.016%

    No Known Activations