© 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. 155016
    Prev
    Next
    INDEX
    Explanations

    non-english words

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

    Following up, based on

    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
    MD
    0.63
    DR
    0.59
    L
    0.57
    op
    0.55
    ND
    0.54
    R
    0.54
    ோ
    0.53
    do
    0.52
    at
    0.52
    M
    0.51
    POSITIVE LOGITS
     Basketball
    0.59
     ترکیب
    0.54
     जितने
    0.52
     मोटरसाइकिल
    0.51
     tujuh
    0.50
     प्लास्टिक
    0.50
    ర్రీ
    0.50
     konsep
    0.49
     একত্রে
    0.48
     डायरेक्टली
    0.48
    Activations Density 0.000%

    No Known Activations