© 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. 34-GEMMASCOPE-RES-131K
    7. 59698
    Prev
    Next
    INDEX
    Explanations

    product, Bag, leaf, scorch, shuffle, Remix, guide, Reject, Redirect, Invalid

    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_34/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
    prada
    -1.29
     farmacé
    -1.18
    mycompany
    -1.17
    gothic
    -1.15
    argentina
    -1.15
    salam
    -1.13
    kimono
    -1.12
     Pozna
    -1.10
    parfum
    -1.09
    converse
    -1.09
    POSITIVE LOGITS
    便利です
    1.07
    ag
    1.04
     leurs
    1.03
    ab
    1.02
    cep
    1.01
    ob
    1.01
    軼
    1.00
    ze
    0.98
    em
    0.96
    を行いました
    0.96
    Activations Density 0.064%

    No Known Activations