© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9682
    Prev
    Next
    INDEX
    Explanations

    unique

    np_acts-logits-general · gemini-2.5-flash-lite

    uniqueness and distinctiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iteits
    0.38
    😫
    0.38
    😰
    0.38
    如果我们
    0.38
     பரப்பு
    0.37
    ន្
    0.37
     करवाए
    0.37
    どんどん
    0.36
     bây
    0.35
    ᒪ
    0.35
    POSITIVE LOGITS
     unique
    2.83
    unique
    2.78
     uniqueness
    2.73
     уника
    2.72
     Unique
    2.67
    Unique
    2.66
     uniques
    2.53
     UNIQUE
    2.50
     uniquely
    2.38
     unik
    2.33
    Activations Density 0.839%

    No Known Activations