© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 210
    Prev
    Next
    INDEX
    Explanations

    Corbin Burnes scientific papers

    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_53_width_65k_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
     occured
    0.40
     occurred
    0.40
     pixel
    0.39
    バー
    0.38
    ("#
    0.37
     স্বাক্ষর
    0.37
     lel
    0.37
     vas
    0.37
     ocur
    0.37
     バー
    0.37
    POSITIVE LOGITS
    sac
    0.46
     Kid
    0.45
    zim
    0.43
    Читати
    0.43
    apia
    0.42
    ází
    0.40
    Sac
    0.39
    𝟰
    0.39
    qua
    0.38
     мед
    0.37
    Activations Density 0.000%

    No Known Activations