© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9558
    Prev
    Next
    INDEX
    Explanations

    content of refusal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     drinking
    0.55
     already
    0.55
    ண
    0.55
    ீர
    0.52
     countless
    0.51
     literary
    0.51
    țin
    0.51
    রক্ষ
    0.50
     books
    0.48
     What
    0.48
    POSITIVE LOGITS
    வ்வேறு
    1.02
     maestro
    1.02
    こちらは
    1.02
     etkisi
    1.00
    分组
    0.97
     문제는
    0.97
     ضلع
    0.96
     전류
    0.95
    ◹
    0.93
    이지만
    0.93
    Activations Density 0.169%

    No Known Activations