© 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. 197424
    Prev
    Next
    INDEX
    Explanations

    grammatical conjunctions and auxiliaries

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

    characteristics

    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
    鍝
    0.53
     Fitbit
    0.51
     IEEE
    0.49
     周
    0.49
     Rajya
    0.48
     École
    0.47
    郏
    0.47
    piration
    0.46
     পর্ব
    0.46
     Triathlon
    0.46
    POSITIVE LOGITS
     characteristics
    0.47
    이
    0.46
     upas
    0.45
     نیست
    0.44
     frost
    0.44
     subjet
    0.44
     levies
    0.43
    หาย
    0.43
    성
    0.43
     decor
    0.42
    Activations Density 0.000%

    No Known Activations