© 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. 15781
    Prev
    Next
    INDEX
    Explanations

    discovering concepts and agreements

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

    links and resources

    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
     eyelids
    0.45
     چشم
    0.41
     huddled
    0.41
     ugly
    0.40
    âteau
    0.39
     sobbing
    0.39
     giddy
    0.39
    ̴
    0.39
     huyết
    0.38
     när
    0.38
    POSITIVE LOGITS
     promotes
    0.52
     provides
    0.51
     empowers
    0.50
    सीएम
    0.49
     includes
    0.47
    នៃ
    0.45
    等が
    0.44
     ASAP
    0.44
     prevede
    0.43
     incluye
    0.43
    Activations Density 0.032%

    No Known Activations