© 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. 28174
    Prev
    Next
    INDEX
    Explanations

    leaking information and whistleblowers

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

    hyena and leaks

    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
    猙
    0.43
     สะ
    0.43
     knot
    0.43
    вин
    0.42
     knots
    0.42
    สะ
    0.41
    烘
    0.41
     गणपति
    0.40
    телни
    0.40
     quick
    0.40
    POSITIVE LOGITS
    泄漏
    0.74
     leaking
    0.72
     leak
    0.70
    洩
    0.68
     leaked
    0.68
     Leak
    0.67
     leaks
    0.66
    Leak
    0.66
     whistleblower
    0.65
    泄
    0.65
    Activations Density 0.030%

    No Known Activations