© 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. 31-GEMMASCOPE-2-RES-262K
    7. 21862
    Prev
    Next
    INDEX
    Explanations

    Home Computer Glass Bank Microsoft Free

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

    titles and descriptions with pipes

    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_31_width_262k_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
    Α
    0.50
    
    0.50
    Ꮁ
    0.48
    成り
    0.47
    Ⴀ
    0.47
    ეხ
    0.45
    ไปยัง
    0.45
    可以说是
    0.45
    亍
    0.45
    截图
    0.44
    POSITIVE LOGITS
     politik
    0.46
     Dinesh
    0.44
    kinson
    0.40
     Dodge
    0.39
     οικονομ
    0.39
     फरक
    0.39
     medy
    0.39
     dodge
    0.39
     Darren
    0.38
     refundable
    0.38
    Activations Density 0.003%

    No Known Activations