© 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. 79979
    Prev
    Next
    INDEX
    Explanations

    property features and locations

    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
    ícias
    -1.45
    estaba
    -1.39
    ueuse
    -1.38
    ymbol
    -1.37
     peuvent
    -1.34
    Locatie
    -1.30
    Folge
    -1.26
    が違う
    -1.25
     estadía
    -1.24
     alcuni
    -1.23
    POSITIVE LOGITS
     extensive
    1.27
    ˃
    1.23
    様な
    1.22
     like
    1.20
     access
    1.20
     közel
    1.20
     full
    1.15
     well
    1.15
    I
    1.15
     Like
    1.13
    Activations Density 0.022%

    No Known Activations