© 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. 243499
    Prev
    Next
    INDEX
    Explanations

    film festival, party bus, picture frames

    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
     gradually
    0.46
     gently
    0.46
     monthly
    0.45
    小さな
    0.44
     еже
    0.44
     mildly
    0.43
     и
    0.43
    quasi
    0.43
    monthly
    0.42
    ざ
    0.42
    POSITIVE LOGITS
     তখনও
    0.50
     পরেই
    0.48
     중에
    0.46
     zusätzliche
    0.46
    भेद
    0.45
     আগেও
    0.45
    仍在
    0.45
     बेरोजगारी
    0.44
     کیونکہ
    0.43
    已经
    0.43
    Activations Density 0.001%

    No Known Activations