© 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. 9818
    Prev
    Next
    INDEX
    Explanations

    `com.example.` packages

    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
     trattano
    -1.25
     différentes
    -1.16
     différents
    -1.10
     ort
    -1.06
     molti
    -1.05
    opie
    -1.03
     olu
    -1.03
     slike
    -1.02
     diversos
    -1.02
     berbagai
    -1.01
    POSITIVE LOGITS
     sparkly
    1.21
    !
    1.13
     ghastly
    1.13
     showy
    1.11
    贵族
    1.09
     даже
    1.09
    <>
    1.08
     legume
    1.05
     seductive
    1.03
     originaux
    1.02
    Activations Density 0.002%

    No Known Activations