© 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. 90598
    Prev
    Next
    INDEX
    Explanations

    comparable to

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

    when or if

    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
     catheters
    0.49
    浏览器
    0.42
    镗
    0.42
     resistencias
    0.41
     necessárias
    0.41
     yaitu
    0.41
    คือ
    0.41
    烦
    0.40
    籹
    0.40
     ():
    0.39
    POSITIVE LOGITS
    DEBUGFS
    0.50
     особли
    0.48
     البعض
    0.46
     तिजारत
    0.46
     могло
    0.46
    izel
    0.45
     improbable
    0.45
     suyo
    0.45
    주일
    0.44
    epart
    0.44
    Activations Density 0.001%

    No Known Activations