© 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. 61808
    Prev
    Next
    INDEX
    Explanations

    numbers and currencies

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

    accommodate variable descriptors

    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
     brag
    0.46
    І
    0.44
    子は
    0.43
     why
    0.43
     godly
    0.43
     crusade
    0.42
     laborious
    0.42
     probation
    0.41
     go
    0.41
     remedy
    0.40
    POSITIVE LOGITS
     слегка
    0.57
     оригина
    0.55
     აღმასრულ
    0.53
     পরিসংখ্যান
    0.52
     деталей
    0.51
     ಘ
    0.50
     légèrement
    0.50
     όπως
    0.50
     المقرر
    0.50
     нескольких
    0.50
    Activations Density 0.000%

    No Known Activations