© 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. 86194
    Prev
    Next
    INDEX
    Explanations

    uint integer types

    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
    '
    -2.44
     You
    -2.34
     zusätz
    -2.22
    訁
    -2.08
     übri
    -2.05
     Таким
    -1.98
    应该
    -1.97
     weichen
    -1.95
     culmination
    -1.94
     Gegenstände
    -1.92
    POSITIVE LOGITS
     and
    2.44
    芣
    2.03
    »?
    1.98
    ;?
    1.98
    :
    1.95
     of
    1.85
    垸
    1.80
     solucion
    1.79
    ﻬ
    1.79
     navideño
    1.74
    Activations Density 0.005%

    No Known Activations