© 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. 22-GEMMASCOPE-RES-131K
    7. 95755
    Prev
    Next
    INDEX
    Explanations

    AF_

    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
    ಝ
    -1.19
    难受
    -1.14
     häm
    -1.04
    testng
    -1.00
    jego
    -0.99
    に行ってきました
    -0.99
     contactez
    -0.97
    を行い
    -0.96
    বং
    -0.91
    “……
    -0.91
    POSITIVE LOGITS
    attendre
    1.11
    koneksi
    1.09
     puramente
    1.08
    tapis
    1.06
     anything
    1.00
    や
    0.99
    jds
    0.98
    –>
    0.97
    regi
    0.96
     anymore
    0.95
    Activations Density 0.002%

    No Known Activations