© 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. 31-GEMMASCOPE-2-RES-262K
    7. 40493
    Prev
    Next
    INDEX
    Explanations

    "your mother" joke

    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_31_width_262k_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
     notables
    0.51
     authorise
    0.50
    제곱
    0.47
     kér
    0.46
     fotograf
    0.46
     két
    0.46
    喻
    0.45
     conferma
    0.45
     pedra
    0.45
     graves
    0.44
    POSITIVE LOGITS
     стиля
    0.47
    ⑰
    0.47
     пово
    0.45
    )])
    0.45
    )"))
    0.44
    chnet
    0.44
     ولی
    0.43
     огромное
    0.43
    oyloxy
    0.42
    ស្ថានភាព
    0.42
    Activations Density 0.001%

    No Known Activations