© 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. 68000
    Prev
    Next
    INDEX
    Explanations

    foreign and technical terms

    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
     if
    -1.20
     garner
    -1.17
     revital
    -1.13
    urée
    -1.10
    ～♪
    -1.08
    Поэтому
    -1.08
     pesta
    -1.07
     dikutip
    -1.04
     new
    -1.03
    ᳝
    -1.03
    POSITIVE LOGITS
    .
    1.37
     MANY
    1.32
    —-
    1.26
     lác
    1.24
    絝
    1.20
     trám
    1.20
     réfrigérateur
    1.20
     VERY
    1.20
     extremely
    1.17
     ウエスト
    1.16
    Activations Density 0.027%

    No Known Activations