© 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
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 42114
    Prev
    Next
    INDEX
    Explanations

    Euromaidan Yanukovych agreement

    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_16_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
     rooster
    0.62
     Y
    0.62
     set
    0.57
     hand
    0.57
     TIME
    0.56
     time
    0.55
     really
    0.54
     T
    0.54
     on
    0.53
     sache
    0.53
    POSITIVE LOGITS
    ون
    0.60
    ርዝ
    0.59
    લ
    0.57
    夶
    0.57
    كي
    0.55
    綺
    0.55
    ൭
    0.55
    接觸
    0.55
    منت
    0.54
     plabic
    0.54
    Activations Density 0.008%

    No Known Activations