© 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-65K
    7. 55209
    Prev
    Next
    INDEX
    Explanations

    hacking and security bypasses

    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_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
    3
    0.59
     Familiar
    0.52
    7
    0.51
    6
    0.48
    familiar
    0.47
    9
    0.46
    5
    0.45
    4
    0.44
    Warnings
    0.43
    ↵
    0.42
    POSITIVE LOGITS
    ၊
    0.43
     말고
    0.42
    entrop
    0.41
    橡胶
    0.40
     μία
    0.39
     경쟁
    0.39
    䄪
    0.39
     공개
    0.39
    ㅡ
    0.38
     будущего
    0.38
    Activations Density 0.008%

    No Known Activations