© 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. 13151
    Prev
    Next
    INDEX
    Explanations

    Quebec City

    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
    a
    1.91
    ar
    1.49
    u
    1.47
    ing
    1.43
    w
    1.34
    il
    1.23
    as
    1.16
    un
    1.16
    y
    1.16
    ir
    1.16
    POSITIVE LOGITS
     to
    0.99
    檚
    0.86
     at
    0.80
    У
    0.79
     سي
    0.77
    ፈር
    0.77
    月份
    0.77
    يا
    0.76
     zusätzlichen
    0.74
    Но
    0.72
    Activations Density 0.002%

    No Known Activations