© 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. 73854
    Prev
    Next
    INDEX
    Explanations

    later year fry interactive Engineer

    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
     أيضًا
    -1.21
    Hvordan
    -1.18
    不仅
    -1.18
    Additionally
    -1.18
     Légion
    -1.17
    Thankfully
    -1.17
     internetu
    -1.16
    從
    -1.15
    WITH
    -1.14
     огром
    -1.14
    POSITIVE LOGITS
     at
    1.13
    riors
    1.13
     often
    1.13
    gradable
    1.10
    閉じ
    1.10
    描いた
    1.09
    岀
    1.07
    ishness
    1.03
    textTheme
    1.02
    (\%)
    1.01
    Activations Density 0.164%

    No Known Activations