© 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. 36703
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
    ztes
    -1.47
    もありました
    -1.29
     книгу
    -1.28
    ENTH
    -1.23
    oluble
    -1.20
    ,
    -1.20
    InputBorder
    -1.18
    オブ
    -1.16
     dix
    -1.13
    もあった
    -1.13
    POSITIVE LOGITS
     what
    1.38
     рік
    1.11
     leveraging
    1.11
     If
    1.09
     not
    1.08
     your
    1.08
     infamous
    1.07
    !!!!!
    1.07
     H
    1.06
     Despite
    1.05
    Activations Density 0.302%

    No Known Activations