© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16151
    Prev
    Next
    INDEX
    Explanations

    time measuring

    np_acts-logits-general · gemini-2.5-flash-lite

    recession email door plastic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Altri
    0.47
    创立
    0.44
    边
    0.43
    Button
    0.42
     ПРО
    0.42
    clientID
    0.42
    IDField
    0.42
    ારા
    0.41
    sina
    0.41
    LIMIT
    0.41
    POSITIVE LOGITS
    ية
    0.53
    ਟ
    0.53
     averages
    0.52
     swipes
    0.47
     erreurs
    0.47
     spits
    0.46
     intermediaries
    0.46
     outliers
    0.45
     invers
    0.45
     Spitz
    0.45
    Activations Density 0.001%

    No Known Activations