Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 3025
    Prev
    Next
    INDEX
    Explanations

    refusing 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-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GitLab
    0.43
    getTable
    0.37
    会在
    0.37
     الدولي
    0.36
    greSQL
    0.36
     স্বর্গ
    0.35
    ng
    0.35
    ⟫
    0.35
    емом
    0.34
    त्री
    0.34
    POSITIVE LOGITS
    祗
    0.37
     Conditioning
    0.37
     ব্যা
    0.35
    ஒ
    0.35
    音楽
    0.34
    サラ
    0.34
    жени
    0.34
    addListener
    0.33
     হাতি
    0.33
     Klar
    0.33
    Activations Density 0.001%

    No Known Activations