© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7153
    Prev
    Next
    INDEX
    Explanations

    abstract section

    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
     Penyakit
    -2.42
    蕷
    -1.98
    ?"
    -1.96
     Apabila
    -1.86
     When
    -1.83
    鸰
    -1.76
     if
    -1.76
     by
    -1.70
     Mereka
    -1.68
     designated
    -1.66
    POSITIVE LOGITS
    abstract
    1.98
     Experienced
    1.98
    廪
    1.97
     empêcher
    1.97
    while
    1.95
     花纹
    1.95
     présidenti
    1.95
    Isn
    1.93
    Hmmm
    1.87
    roughly
    1.87
    Activations Density 0.010%

    No Known Activations