© 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. 104226
    Prev
    Next
    INDEX
    Explanations

    nullable and optional values

    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
    seemed
    -1.48
    皷
    -1.28
     règlement
    -1.27
    棡
    -1.27
    翃
    -1.26
     surpris
    -1.25
    糁
    -1.23
     laug
    -1.22
    隳
    -1.22
    และ
    -1.20
    POSITIVE LOGITS
    ’
    1.37
     long
    1.34
     p
    1.25
    \
    1.16
    .”
    1.16
    C
    1.16
     high
    1.16
     l
    1.13
     military
    1.13
    de
    1.12
    Activations Density 0.001%

    No Known Activations