© 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. 236167
    Prev
    Next
    INDEX
    Explanations

    in the category

    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
    교
    0.50
    IFF
    0.49
    UTO
    0.49
    CHK
    0.49
    IENT
    0.48
    ých
    0.48
    ESA
    0.46
    IGA
    0.46
     דבר
    0.46
     merger
    0.46
    POSITIVE LOGITS
     গিয়েছিল
    0.49
    发明
    0.45
     গিয়েছিল
    0.44
    omile
    0.42
    >((
    0.38
    していました
    0.38
    できました
    0.38
    しかった
    0.38
    偒
    0.38
     comerciales
    0.37
    Activations Density 0.001%

    No Known Activations