© 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. 196036
    Prev
    Next
    INDEX
    Explanations

    targeted surveillance

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

    (〃´∪｀〃)ゞ gesture or emoti-icon

    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
    佬
    0.52
    اعه
    0.51
    ртка
    0.49
    न्देल
    0.48
    俏
    0.48
    زن
    0.48
    င်း
    0.47
    ف
    0.47
    惫
    0.47
     POLITICAL
    0.46
    POSITIVE LOGITS
    om
    0.55
    um
    0.54
    Wah
    0.52
     Wah
    0.50
    si
    0.49
    ey
    0.49
    plication
    0.49
    stag
    0.48
     ndi
    0.48
    ie
    0.47
    Activations Density 0.000%

    No Known Activations