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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13596
    Prev
    Next
    INDEX
    Explanations

    scan ips range vulnerabilities

    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_31_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
     politič
    0.60
    کل
    0.52
     політи
    0.52
     régime
    0.50
     nước
    0.49
    বর্ষ
    0.49
    𝕡
    0.49
     diplomatic
    0.48
     فہرست
    0.48
     تبدیلی
    0.48
    POSITIVE LOGITS
    1
    0.49
    s
    0.49
     (
    0.46
     using
    0.44
    (
    0.43
     terminated
    0.41
    Rates
    0.41
     Rats
    0.41
     am
    0.40
     terminate
    0.39
    Activations Density 0.018%

    No Known Activations