© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 998
    Prev
    Next
    INDEX
    Explanations

    vulgar or aggressive speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    💗
    0.61
    ☺️
    0.59
    🌸
    0.57
     wonderful
    0.56
    😊
    0.56
    💖
    0.55
    💓
    0.54
    🌟
    0.52
    ❣️
    0.52
    😢
    0.50
    POSITIVE LOGITS
     pissed
    1.00
     piss
    0.87
     bullshit
    0.86
     booze
    0.81
    Fuck
    0.80
     shit
    0.79
    俺
    0.79
    damn
    0.79
     asshole
    0.78
     shitty
    0.78
    Activations Density 0.528%

    No Known Activations