© 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. 95494
    Prev
    Next
    INDEX
    Explanations

    Macau Open, Eureka!, Q:, This invention

    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
     my
    -1.45
     nggak
    -1.25
     τὴν
    -1.18
     angusti
    -1.15
    ֺ
    -1.14
     Theologie
    -1.10
    𝗂
    -1.10
     poderosa
    -1.09
    pēc
    -1.08
     England
    -1.07
    POSITIVE LOGITS
    ᾽
    1.28
    🪛
    1.27
    Untuk
    1.26
    וּ
    1.23
    🩹
    1.22
    Nowadays
    1.20
     betreft
    1.19
     žem
    1.18
    ּוֹ
    1.18
    Heute
    1.18
    Activations Density 0.000%

    No Known Activations