© 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-262K
    7. 32506
    Prev
    Next
    INDEX
    Explanations

    paperclip maximizer, paper title, paper stealth

    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_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
    to
    0.51
    ت
    0.50
    tions
    0.48
     ब्लॉ
    0.48
    को
    0.47
    कांना
    0.45
    下に
    0.45
    үүн
    0.44
    یک
    0.43
    tion
    0.43
    POSITIVE LOGITS
    Paper
    0.66
    Pap
    0.59
     Paper
    0.59
    Trail
    0.56
    pap
    0.56
    纸
    0.55
    clip
    0.55
    紙
    0.54
    papers
    0.54
    Papers
    0.54
    Activations Density 0.006%

    No Known Activations