© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75524
    Prev
    Next
    INDEX
    Explanations

    refusal of harmful roleplay requests

    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
     occasionally
    0.42
     সাহেব
    0.41
    дые
    0.41
    annen
    0.40
    在
    0.40
     aján
    0.39
     heavens
    0.39
     groceries
    0.38
    ўні
    0.38
    ді
    0.38
    POSITIVE LOGITS
     bipartite
    0.45
    ਰ
    0.44
     Similarity
    0.43
     Gesamt
    0.43
     totalitarian
    0.43
     bols
    0.43
     फंडिंग
    0.43
     Bolshevik
    0.42
     subalgebras
    0.42
    POINTS
    0.42
    Activations Density 0.010%

    No Known Activations