© 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. 95701
    Prev
    Next
    INDEX
    Explanations

    mathematical subset notation

    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
    .
    -2.63
    ,
    -1.48
     "
    -1.38
    fro
    -1.34
    𝗦
    -1.27
    geführt
    -1.23
     they
    -1.23
    好的
    -1.22
    tholes
    -1.21
    などで
    -1.20
    POSITIVE LOGITS
    Zubereitung
    1.88
    もともと
    1.60
     assistenza
    1.57
    。
    1.56
     accordance
    1.56
    Beskrivning
    1.55
    媖
    1.55
     methodologies
    1.53
     illustrazione
    1.52
    Πηγή
    1.52
    Activations Density 0.014%

    No Known Activations