© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 55863
    Prev
    Next
    INDEX
    Explanations

    The whole

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

    refusal of harmful requests

    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
    notch
    0.46
     I
    0.46
     enough
    0.44
     span
    0.42
    ंटे
    0.41
     chuy
    0.41
     mistake
    0.40
     Baba
    0.40
     improved
    0.40
     $
    0.39
    POSITIVE LOGITS
     言っ
    0.51
     विद्यार्थ्यांनी
    0.50
     अथवा
    0.50
     সূত্রের
    0.48
     потребности
    0.48
     смерти
    0.48
    各位同學
    0.48
     образования
    0.47
     উদ্দেশ্যে
    0.47
    ুয়ারি
    0.47
    Activations Density 0.000%

    No Known Activations