© 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. 28017
    Prev
    Next
    INDEX
    Explanations

    statistical and scientific topics

    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
     tirantes
    -1.20
    centerline
    -1.16
     военных
    -1.15
     компьютера
    -1.14
     cantidades
    -1.12
    レーター
    -1.09
     behauptet
    -1.09
     trastornos
    -1.09
    じゃん
    -1.09
     conductas
    -1.09
    POSITIVE LOGITS
     in
    1.55
     across
    1.34
    jną
    1.06
     бампер
    0.98
    волю
    0.98
    及其
    0.98
     både
    0.97
    ethers
    0.94
     оптима
    0.92
    Será
    0.91
    Activations Density 0.081%

    No Known Activations