© 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. 34-GEMMASCOPE-RES-131K
    7. 119075
    Prev
    Next
    INDEX
    Explanations

    on, at, in

    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_34/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
    溴
    -0.77
     ult
    -0.77
     tę
    -0.77
    Sé
    -0.76
     kanan
    -0.75
     animaux
    -0.75
     телефон
    -0.74
    zott
    -0.74
     Comun
    -0.73
     Tuf
    -0.73
    POSITIVE LOGITS
     merits
    1.00
     capping
    0.80
     Bismarck
    0.78
     sublimation
    0.75
     merit
    0.73
     ._
    0.73
    capped
    0.71
     capped
    0.71
     firsthand
    0.70
    ♂
    0.69
    Activations Density 0.011%

    No Known Activations