© 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. 15838
    Prev
    Next
    INDEX
    Explanations

    alphabetical order, year, connection

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

    injury, accident, or death

    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
    ed
    0.58
    4
    0.55
    _
    0.54
    ountain
    0.52
    B
    0.51
    Parliament
    0.50
        
    0.50
    5
    0.50
    L
    0.48
    শ
    0.48
    POSITIVE LOGITS
     apporter
    0.53
     trouva
    0.52
     لگانے
    0.49
     पवार
    0.48
     lucrat
    0.48
     regalías
    0.47
    醿
    0.46
     والاست
    0.46
     basa
    0.46
     personne
    0.45
    Activations Density 0.000%

    No Known Activations