© 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. 59675
    Prev
    Next
    INDEX
    Explanations

    javadoc/JavaScript en

    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
     nécessité
    -1.85
     to
    -1.52
     Fünf
    -1.46
     how
    -1.45
     beschä
    -1.44
    鞏
    -1.43
     手順
    -1.42
     воло
    -1.40
    了一個
    -1.40
     need
    -1.39
    POSITIVE LOGITS
    +}$
    1.78
     delikat
    1.72
     maíz
    1.52
     cereales
    1.52
    ropractor
    1.49
     = 
    1.45
     metody
    1.43
    bilden
    1.43
    :],
    1.42
    wanderung
    1.42
    Activations Density 0.046%

    No Known Activations