© 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. 129444
    Prev
    Next
    INDEX
    Explanations

    multilingual content or specific phrases

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

    software, influence, concatenate

    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
     expected
    0.50
    은
    0.49
    노
    0.49
     absolutely
    0.48
     conformance
    0.47
    нома
    0.46
    で
    0.46
    아
    0.46
    έα
    0.45
    א
    0.45
    POSITIVE LOGITS
     Général
    0.46
     ఫలి
    0.44
     çalışmaları
    0.44
     कराने
    0.43
     činn
    0.43
    活動
    0.43
    irties
    0.43
    ChatGPT
    0.43
    bullying
    0.43
     கல்விய
    0.42
    Activations Density 0.001%

    No Known Activations