© 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. 240182
    Prev
    Next
    INDEX
    Explanations

    either followed by conjunction or punctuation

    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
    6
    0.50
    当社
    0.48
     کیلئے
    0.46
    یکس
    0.45
    ای
    0.45
     Nickel
    0.45
    اع
    0.44
    ٹر
    0.44
    頂きました
    0.44
    Snow
    0.43
    POSITIVE LOGITS
     不能
    0.48
    GORITH
    0.47
    eclampsia
    0.47
     Archivlink
    0.46
     mastered
    0.45
     प्रतियोगिता
    0.45
    嘤
    0.44
     或
    0.44
    cccn
    0.43
    shen
    0.43
    Activations Density 0.001%

    No Known Activations