© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10212
    Prev
    Next
    INDEX
    Explanations

    cheat detection

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

    technical documentation and code implementation patterns.

    oai_token-act-pair · claude-4-5-haikuTriggered by @cam

    video games

    np_max-act · claude-4-5-haikuTriggered by @cam

    cheat codes

    np_max-act-logits · claude-4-5-haikuTriggered by @cam
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_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
     dungeon
    0.45
     guild
    0.44
     guilds
    0.44
     Kickstarter
    0.44
     Pixel
    0.43
     Guild
    0.42
    Guild
    0.42
    ifico
    0.41
     steampunk
    0.40
     pixel
    0.40
    POSITIVE LOGITS
     cheat
    0.76
     cheats
    0.71
     cheating
    0.70
     Cheat
    0.66
     cheated
    0.65
    cheat
    0.64
    CHEAT
    0.60
    Cheat
    0.55
     undetected
    0.45
     Che
    0.45
    Activations Density 0.126%

    No Known Activations