© 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. 106860
    Prev
    Next
    INDEX
    Explanations

    foreign language or script

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

    air entering lungs

    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
    dict
    0.49
    na
    0.49
    tu
    0.48
     shuttle
    0.48
    c
    0.48
    pol
    0.46
     lite
    0.46
     Orient
    0.46
    descr
    0.46
    do
    0.45
    POSITIVE LOGITS
     गवर्नर
    0.51
    zené
    0.46
    攷
    0.46
     जिलाधिकारी
    0.46
    音
    0.45
    ቝ
    0.44
     असमान
    0.43
     वार्षिक
    0.43
    呷
    0.42
     सालाना
    0.42
    Activations Density 0.001%

    No Known Activations