© 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. 181501
    Prev
    Next
    INDEX
    Explanations

    Bradley Effect refers to

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

    actions and consequences

    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
    ará
    0.54
     latach
    0.52
    래
    0.49
     okaza
    0.48
     পেরিয়ে
    0.48
    ovať
    0.47
     書い
    0.47
    ﻄ
    0.47
     désigne
    0.46
    évén
    0.46
    POSITIVE LOGITS
     Approved
    0.57
     Defense
    0.55
     Storage
    0.55
     Efficiency
    0.52
     Scientific
    0.51
     Furniture
    0.50
     Weapons
    0.49
     Student
    0.49
     Defence
    0.49
     Administration
    0.48
    Activations Density 0.000%

    No Known Activations