© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 27422
    Prev
    Next
    INDEX
    Explanations

    after certain verbs

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

    logic gates and excuses

    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
    ション
    0.44
    Neben
    0.42
    もしくは
    0.40
     Prend
    0.40
     ಹಾಗೂ
    0.39
     उल्लेख
    0.39
    ූ
    0.39
     noticeably
    0.39
    Ⴌ
    0.38
     pertin
    0.38
    POSITIVE LOGITS
     booths
    0.43
     intram
    0.42
     Arthritis
    0.42
     AIDS
    0.41
     teamwork
    0.40
     caches
    0.40
     Kentucky
    0.39
     That
    0.39
     تح
    0.39
     Iowa
    0.39
    Activations Density 0.000%

    No Known Activations