© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 31108
    Prev
    Next
    INDEX
    Explanations

    word pairings and phrases

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

    describing contexts or adjacencies

    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_262k_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
    不利
    0.48
    ณ
    0.47
    Listo
    0.47
     വാഹന
    0.46
    目的地
    0.46
     لاءِ
    0.46
    лії
    0.44
     prestazioni
    0.44
    書法
    0.44
     ਜਾਣ
    0.43
    POSITIVE LOGITS
     -
    0.49
     Spice
    0.49
    0.47
     DNA
    0.47
     Edinburgh
    0.46
     Anglic
    0.46
     Dinner
    0.44
     magic
    0.44
     Forget
    0.43
     Same
    0.43
    Activations Density 0.000%

    No Known Activations