© 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. 49406
    Prev
    Next
    INDEX
    Explanations

    compound words or phrases

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

    what happened

    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
     הג
    0.48
     მთავ
    0.48
    ა
    0.48
    spiele
    0.47
    ė
    0.46
    deki
    0.45
    Brexit
    0.44
    ਾ
    0.44
    ས
    0.44
    İ
    0.44
    POSITIVE LOGITS
     Henderson
    0.49
     unquestionably
    0.48
     مرتبہ
    0.48
     vesting
    0.46
     continuando
    0.46
     Peyton
    0.45
     constitutes
    0.45
     surety
    0.45
    持续
    0.44
     Christensen
    0.44
    Activations Density 0.000%

    No Known Activations