© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 16260
    Prev
    Next
    INDEX
    Explanations

    refusal and termination

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

    refusal or rejection

    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_16k_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
    惚
    0.42
    consol
    0.40
    ದಗ
    0.40
     oprav
    0.40
     বাড়
    0.39
     बढ़ी
    0.39
     সন্ত
    0.39
     вклю
    0.38
    account
    0.38
     ожи
    0.37
    POSITIVE LOGITS
    拒绝
    1.48
    拒
    1.46
     rejection
    1.45
     reject
    1.43
     refusal
    1.42
     rejecting
    1.38
     refus
    1.38
     rejects
    1.37
     rifi
    1.37
     رفض
    1.37
    Activations Density 0.806%

    No Known Activations