© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119503
    Prev
    Next
    INDEX
    Explanations

    created by

    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
     the
    -2.09
    feliz
    -1.42
     our
    -1.40
     for
    -1.37
    ต่างๆ
    -1.36
     geweldig
    -1.34
     produisons
    -1.30
    ₓ
    -1.30
    fatter
    -1.29
     these
    -1.27
    POSITIVE LOGITS
    xial
    1.40
     ”
    1.38
     arrêté
    1.36
    "]();
    1.33
    mathcal
    1.33
    liflower
    1.32
    enciado
    1.30
    atherapy
    1.30
    Raising
    1.30
    xido
    1.30
    Activations Density 0.133%

    No Known Activations