© 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. 15804
    Prev
    Next
    INDEX
    Explanations

    metadata or descriptors

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

    titles and labels

    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
     up
    0.47
     exposed
    0.46
    entially
    0.45
     levels
    0.44
    s
    0.44
    istically
    0.43
    :*
    0.43
    eles
    0.42
    line
    0.42
    verage
    0.42
    POSITIVE LOGITS
    ğraf
    0.50
     vittime
    0.47
     víctimas
    0.46
    мов
    0.45
     transaksi
    0.45
     表
    0.43
     cụ
    0.43
    Untitled
    0.43
    යන්
    0.42
     لوڈ
    0.42
    Activations Density 0.019%

    No Known Activations