© 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. 53-GEMMASCOPE-2-RES-262K
    7. 47359
    Prev
    Next
    INDEX
    Explanations

    exploit, abuse or

    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_53_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
    Razor
    0.39
    emu
    0.38
    戞
    0.38
    ρυ
    0.37
    Bread
    0.37
     consular
    0.37
     Rhin
    0.37
    աց
    0.36
    ణ్
    0.36
    빵
    0.36
    POSITIVE LOGITS
     suck
    0.39
     कैरी
    0.38
     కో
    0.38
     göre
    0.38
     Derek
    0.37
     Dod
    0.36
     Dave
    0.35
    देखो
    0.35
     silk
    0.35
     Repeat
    0.34
    Activations Density 0.004%

    No Known Activations