© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 84470
    Prev
    Next
    INDEX
    Explanations

    cleared to enter, bill, everything else

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

    ignore previous instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ฝ
    0.49
     காற்றின்
    0.48
     ночь
    0.47
     vaik
    0.47
     후
    0.47
    мир
    0.46
     сентября
    0.45
     маль
    0.45
     дня
    0.45
     вересня
    0.45
    POSITIVE LOGITS
    向
    0.48
     trasform
    0.45
    dotenv
    0.45
     fosse
    0.44
     hurled
    0.44
     sliced
    0.44
     crypto
    0.43
     vanuit
    0.43
    传入
    0.43
     Patreon
    0.42
    Activations Density 0.001%

    No Known Activations