© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68417
    Prev
    Next
    INDEX
    Explanations

    Q: or <?php

    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_22/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
     institucional
    -0.98
    Bisous
    -0.94
     since
    -0.91
    काश
    -0.90
    ˂
    -0.87
    一方で
    -0.85
    xnn
    -0.85
    上げて
    -0.84
    徳島
    -0.83
     MURRAY
    -0.83
    POSITIVE LOGITS
    了一遍
    1.13
    了一会儿
    1.13
    了一句
    1.07
    ஆ
    1.02
    Это
    0.98
     drodze
    0.95
    Angebot
    0.95
     appelés
    0.94
     gearbeitet
    0.94
     gesammelt
    0.93
    Activations Density 0.001%

    No Known Activations