© 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. 39750
    Prev
    Next
    INDEX
    Explanations

    programming type declarations

    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
    pherds
    -1.23
     PUSTAKA
    -1.20
    --"
    -1.16
     attribué
    -1.11
    ($__
    -1.09
    Jeśli
    -1.09
    nextProps
    -1.08
    ⎔
    -1.07
    vete
    -1.06
     botella
    -1.06
    POSITIVE LOGITS
     you
    1.58
     môžu
    1.27
    2
    1.25
    5
    1.22
     he
    1.19
     ۱۴۰۰
    1.13
     hän
    1.13
    3
    1.09
     môžete
    1.08
    呪術
    1.07
    Activations Density 0.001%

    No Known Activations