© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25367
    Prev
    Next
    INDEX
    Explanations

    preventing victim defense

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

    structured, emphasized tokens such as headings/labels, quoted or apostrophized text, and numerals/units that mark key or enumerated information.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    ಸ್
    0.40
    
    0.39
    和
    0.39
    <0xE7>
    0.39
    ्रेडिट
    0.37
    ್
    0.37
    菓
    0.37
    тке
    0.37
    ере
    0.36
    、
    0.35
    POSITIVE LOGITS
     POC
    0.35
     Ideal
    0.33
     tomto
    0.32
     Dream
    0.32
     Labrenzia
    0.32
    offsetLeft
    0.32
     نئے
    0.32
     vorge
    0.32
     ہوا
    0.31
     Quantum
    0.31
    Activations Density 0.220%

    No Known Activations