© 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. 107809
    Prev
    Next
    INDEX
    Explanations

    download then

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

    unethical and illegal

    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
     情况
    0.53
    ative
    0.52
    进而
    0.49
     kleines
    0.48
    清除
    0.45
    邃
    0.45
     него
    0.45
     неё
    0.44
     Результа
    0.44
     去
    0.44
    POSITIVE LOGITS
     personnel
    0.56
     firearm
    0.52
     airborne
    0.51
    offic
    0.51
     contribution
    0.51
     personel
    0.50
     executives
    0.49
     macroeconomic
    0.48
     bureaucratic
    0.48
     indemn
    0.48
    Activations Density 0.003%

    No Known Activations