© 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. 122143
    Prev
    Next
    INDEX
    Explanations

    dates and specific events

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

    explaining NSFW refusal

    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
    adese
    0.51
     电
    0.50
    himanyu
    0.50
    owers
    0.48
    hauses
    0.48
    鹕
    0.47
     Orion
    0.46
    inor
    0.46
    tons
    0.46
    fehlung
    0.46
    POSITIVE LOGITS
    ﻦ
    0.50
     basically
    0.46
    ிலேயே
    0.46
    жня
    0.46
    Ᏼ
    0.45
     находя
    0.45
     Dezember
    0.45
    ὄ
    0.45
     bygone
    0.44
    з
    0.44
    Activations Density 0.000%

    No Known Activations